{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5REURI35HW7TZ3MHVQVXCOB5AX","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":"458030d49991b575a80f4af11c45b9470940bfd4d9c7d73f285035848e165f1a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-20T12:26:41Z","title_canon_sha256":"2eadaf98b0a806d0965987715b0c306afd8ec671bcd9601492ac9bea9adc6c30"},"schema_version":"1.0","source":{"id":"2305.12182","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.12182","created_at":"2026-07-05T06:46:04Z"},{"alias_kind":"arxiv_version","alias_value":"2305.12182v2","created_at":"2026-07-05T06:46:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.12182","created_at":"2026-07-05T06:46:04Z"},{"alias_kind":"pith_short_12","alias_value":"5REURI35HW7T","created_at":"2026-07-05T06:46:04Z"},{"alias_kind":"pith_short_16","alias_value":"5REURI35HW7TZ3MH","created_at":"2026-07-05T06:46:04Z"},{"alias_kind":"pith_short_8","alias_value":"5REURI35","created_at":"2026-07-05T06:46:04Z"}],"graph_snapshots":[{"event_id":"sha256:8f698eba7e814daf80945027b1b701eba0d4e362a2e0ff1002bd89b6f1fd2b8d","target":"graph","created_at":"2026-07-05T06:46:04Z","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/2305.12182/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The NLP community has mainly focused on scaling Large Language Models (LLMs) vertically, i.e., making them better for about 100 languages. We instead scale LLMs horizontally: we create, through continued pretraining, Glot500-m, an LLM that covers 511 predominantly low-resource languages. An important part of this effort is to collect and clean Glot500-c, a corpus that covers these 511 languages and allows us to train Glot500-m. We evaluate Glot500-m on five diverse tasks across these languages. We observe large improvements for both high-resource and low-resource languages compared to an XLM-R","authors_text":"Amir Hossein Kargaran, Andr\\'e F. T. Martins, Ayyoob Imani, Chunlan Ma, Fran\\c{c}ois Yvon, Helmut Schmid, Hinrich Sch\\\"utze, Masoud Jalili Sabet, Nora Kassner, Peiqin Lin, Silvia Severini","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-20T12:26:41Z","title":"Glot500: Scaling Multilingual Corpora and Language Models to 500 Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.12182","kind":"arxiv","version":2},"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":"sha256:66686f6b676e3018af90cb88bfa67f90e72554a7f4f1f25b06b88390cbc9b10d","target":"record","created_at":"2026-07-05T06:46:04Z","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":"458030d49991b575a80f4af11c45b9470940bfd4d9c7d73f285035848e165f1a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-20T12:26:41Z","title_canon_sha256":"2eadaf98b0a806d0965987715b0c306afd8ec671bcd9601492ac9bea9adc6c30"},"schema_version":"1.0","source":{"id":"2305.12182","kind":"arxiv","version":2}},"canonical_sha256":"ec4948a37d3dbf3ced87ac2b71383d05f31cf2332494f81d99b5ff2c1d59e4de","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ec4948a37d3dbf3ced87ac2b71383d05f31cf2332494f81d99b5ff2c1d59e4de","first_computed_at":"2026-07-05T06:46:04.697249Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:46:04.697249Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ddh2Rf7H2k4BngOxKF/MOXLnXCIecE/8zKbeqT9xCpHNftGzeTyhLxGwpz1IvSGQ0GvejimhPzle63uW43kuBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:46:04.697707Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.12182","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:66686f6b676e3018af90cb88bfa67f90e72554a7f4f1f25b06b88390cbc9b10d","sha256:8f698eba7e814daf80945027b1b701eba0d4e362a2e0ff1002bd89b6f1fd2b8d"],"state_sha256":"5239389dbf88fce1294789cf9c47fa70a764ba2c162b025b68dca0583cd7b649"}