{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Y755KB6LV37IF544U2UDNXNOQF","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":"3adb8136870f2187d4382a307431afc07c7445de6a0eb8c834bc1128b1f62b09","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-09T13:54:22Z","title_canon_sha256":"db78dfadf678b5b957b0aa12792cf52bc443794667f5c8b22cf6927d8f10ba51"},"schema_version":"1.0","source":{"id":"2405.05777","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.05777","created_at":"2026-07-05T08:17:22Z"},{"alias_kind":"arxiv_version","alias_value":"2405.05777v1","created_at":"2026-07-05T08:17:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.05777","created_at":"2026-07-05T08:17:22Z"},{"alias_kind":"pith_short_12","alias_value":"Y755KB6LV37I","created_at":"2026-07-05T08:17:22Z"},{"alias_kind":"pith_short_16","alias_value":"Y755KB6LV37IF544","created_at":"2026-07-05T08:17:22Z"},{"alias_kind":"pith_short_8","alias_value":"Y755KB6L","created_at":"2026-07-05T08:17:22Z"}],"graph_snapshots":[{"event_id":"sha256:1ea46b71840f8f0b94f893a34d60ead9d45f4f58864245f9203437777dd29a58","target":"graph","created_at":"2026-07-05T08:17:22Z","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/2405.05777/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"S\\'ami, an indigenous language group comprising multiple languages, faces digital marginalization due to the limited availability of data and sophisticated language models designed for its linguistic intricacies. This work focuses on increasing technological participation for the S\\'ami language. We draw the attention of the ML community towards the language modeling problem of Ultra Low Resource (ULR) languages. ULR languages are those for which the amount of available textual resources is very low, and the speaker count for them is also very low. ULRLs are also not supported by mainstream La","authors_text":"Dilip K. Prasad, Himanshu Buckchash, Ronny Paul, Shantipriya Parida","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-09T13:54:22Z","title":"Towards a More Inclusive AI: Progress and Perspectives in Large Language Model Training for the S\\'ami Language"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.05777","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:e17184b931895cc78d6a63b1ad138f8e61d6756bbad2ab90a58b3afc68cbd566","target":"record","created_at":"2026-07-05T08:17:22Z","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":"3adb8136870f2187d4382a307431afc07c7445de6a0eb8c834bc1128b1f62b09","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-09T13:54:22Z","title_canon_sha256":"db78dfadf678b5b957b0aa12792cf52bc443794667f5c8b22cf6927d8f10ba51"},"schema_version":"1.0","source":{"id":"2405.05777","kind":"arxiv","version":1}},"canonical_sha256":"c7fbd507cbaefe82f79ca6a836ddae817806b2160722b4c6f92288185aeac0bc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c7fbd507cbaefe82f79ca6a836ddae817806b2160722b4c6f92288185aeac0bc","first_computed_at":"2026-07-05T08:17:22.655724Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:17:22.655724Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QbMRT55rNz2ANXH8I0fOJJsq+wyzwKqj1RsJLQXaeUVR7qqhK1FkGHgjbXJKvhJvEZ1kkOzEr300OZuPKg8ACg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:17:22.656193Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.05777","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e17184b931895cc78d6a63b1ad138f8e61d6756bbad2ab90a58b3afc68cbd566","sha256:1ea46b71840f8f0b94f893a34d60ead9d45f4f58864245f9203437777dd29a58"],"state_sha256":"752c6d40e73efe4ca53b94e1d7afee3645b734a8808c758ecd0f97de2f4ce61a"}