{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:WD2BNU7ATMUK7WVBDCRYVGG3LS","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":"a65a60695b4bafa632cc6f9d29ae59d70a5e8854a42906d306c38f1003199d62","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-16T20:56:15Z","title_canon_sha256":"cc6d263b9f81f4de6db02f9f7e563849007a5e83590e87739df396e79c10dbdb"},"schema_version":"1.0","source":{"id":"2605.17152","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.17152","created_at":"2026-05-20T00:03:42Z"},{"alias_kind":"arxiv_version","alias_value":"2605.17152v1","created_at":"2026-05-20T00:03:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17152","created_at":"2026-05-20T00:03:42Z"},{"alias_kind":"pith_short_12","alias_value":"WD2BNU7ATMUK","created_at":"2026-05-20T00:03:42Z"},{"alias_kind":"pith_short_16","alias_value":"WD2BNU7ATMUK7WVB","created_at":"2026-05-20T00:03:42Z"},{"alias_kind":"pith_short_8","alias_value":"WD2BNU7A","created_at":"2026-05-20T00:03:42Z"}],"graph_snapshots":[{"event_id":"sha256:6dfe183a486c022a4dc16cfa308d4573ac42b5e2c22417279aad2745d18c2639","target":"graph","created_at":"2026-05-20T00:03:42Z","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":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T22:33:23.765050Z","status":"skipped","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T22:01:57.997250Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.17152/integrity.json","findings":[],"snapshot_sha256":"e653107e6118189bcc2e18812e7fb4fbf55be88af0266e1a4704ed666071b5eb","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal LLMs are evolving from vision-language to tri-modality that see, hear, and read, yet pipelines and benchmarks remain English-centric and compute-heavy. The tutorial offers an overview of this emerging research area for multilingual multimodality across text, speech, and vision under limited data/compute budgets, synthesizing foundations, recent multilingual models (PALO, Maya), speech-text LLMs. We cover low-cost data creation/curation; adapter stacks for tri-modal alignment; culture-aware evaluation beyond English and hands on resources for fine-tuning a compact multilingual VLM an","authors_text":"Enamul Hoque Prince, Firoj Alam, Shammur Absar Chowdhury","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-16T20:56:15Z","title":"Multilingual and Multimodal LLMs in the Wild: Building for Low-Resource Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17152","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":"sha256:63e5cce0f7c5324653e13707c22df0b0572877b9a4eefabda96e5b6d3aee9429","target":"record","created_at":"2026-05-20T00:03:42Z","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":"a65a60695b4bafa632cc6f9d29ae59d70a5e8854a42906d306c38f1003199d62","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-16T20:56:15Z","title_canon_sha256":"cc6d263b9f81f4de6db02f9f7e563849007a5e83590e87739df396e79c10dbdb"},"schema_version":"1.0","source":{"id":"2605.17152","kind":"arxiv","version":1}},"canonical_sha256":"b0f416d3e09b28afdaa118a38a98db5c9214485786c1df5298da9225a04e6b20","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b0f416d3e09b28afdaa118a38a98db5c9214485786c1df5298da9225a04e6b20","first_computed_at":"2026-05-20T00:03:42.343663Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:03:42.343663Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YJmgjrsnwquvTvAgqHx5BhSLgYUmW2OH70N/s5EuM0uVJvWomPiAiCSaOxJkREBct0KJ/EmMI1myb507zbRWCg==","signature_status":"signed_v1","signed_at":"2026-05-20T00:03:42.344539Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.17152","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:63e5cce0f7c5324653e13707c22df0b0572877b9a4eefabda96e5b6d3aee9429","sha256:6dfe183a486c022a4dc16cfa308d4573ac42b5e2c22417279aad2745d18c2639"],"state_sha256":"0694d227a999b85b015b88ef1e08314a3f188cf506a4359222a2a09bf774ba85"}