{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TYTJNVXUH4AG5N5XGXQBMQ7MS2","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":"74f217269f00786bc75093298fc34e14a524e01ecb23b32f486cb8ab15be068d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-29T11:50:16Z","title_canon_sha256":"2ff511462df05bd93c77bef3d291504142f4b461a64fcf6fd30256c58784dfec"},"schema_version":"1.0","source":{"id":"2407.00416","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.00416","created_at":"2026-07-05T09:48:34Z"},{"alias_kind":"arxiv_version","alias_value":"2407.00416v2","created_at":"2026-07-05T09:48:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.00416","created_at":"2026-07-05T09:48:34Z"},{"alias_kind":"pith_short_12","alias_value":"TYTJNVXUH4AG","created_at":"2026-07-05T09:48:34Z"},{"alias_kind":"pith_short_16","alias_value":"TYTJNVXUH4AG5N5X","created_at":"2026-07-05T09:48:34Z"},{"alias_kind":"pith_short_8","alias_value":"TYTJNVXU","created_at":"2026-07-05T09:48:34Z"}],"graph_snapshots":[{"event_id":"sha256:ed6d802d468791df3ea35d74443afc28f125b7d24311debf5aa6cc52ff4d7c73","target":"graph","created_at":"2026-07-05T09:48:34Z","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/2407.00416/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Each new generation of English-oriented Large Language Models (LLMs) exhibits enhanced cross-lingual transfer capabilities and significantly outperforms older LLMs on low-resource languages. This prompts the question: Is there a need for LLMs dedicated to a particular low-resource language? We aim to explore this question for Bengali, a low-to-moderate resource Indo-Aryan language native to the Bengal region of South Asia.\n  We compare the performance of open-weight and closed-source LLMs such as LLaMA-3 and GPT-4 against fine-tuned encoder-decoder models across a diverse set of Bengali downst","authors_text":"Hasnaen Adil, Haz Sameen Shahgir, Khondker Salman Sayeed, Ruwad Naswan, Satak Kumar Dey, Tamzeed Mahfuz","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-29T11:50:16Z","title":"Too Late to Train, Too Early To Use? A Study on Necessity and Viability of Low-Resource Bengali LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.00416","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":"sha256:7b1a7ecbfaee2ec6bbc37e452887e5a2d302212cbe525d2852b322f4eb368a63","target":"record","created_at":"2026-07-05T09:48:34Z","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":"74f217269f00786bc75093298fc34e14a524e01ecb23b32f486cb8ab15be068d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-29T11:50:16Z","title_canon_sha256":"2ff511462df05bd93c77bef3d291504142f4b461a64fcf6fd30256c58784dfec"},"schema_version":"1.0","source":{"id":"2407.00416","kind":"arxiv","version":2}},"canonical_sha256":"9e2696d6f43f006eb7b735e01643ec969145eeeff1ef3b43781328c523cc8f38","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9e2696d6f43f006eb7b735e01643ec969145eeeff1ef3b43781328c523cc8f38","first_computed_at":"2026-07-05T09:48:34.061519Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:48:34.061519Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GGjKwzzoqyBkdZloqCSMM7nE8dRR66KccCN6KwxvUBFhHJPzI9/Ap23lc5Ijd1lkNx5BJq5RnumZQG11cYNLAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:48:34.062008Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.00416","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7b1a7ecbfaee2ec6bbc37e452887e5a2d302212cbe525d2852b322f4eb368a63","sha256:ed6d802d468791df3ea35d74443afc28f125b7d24311debf5aa6cc52ff4d7c73"],"state_sha256":"d624a1105dbb8ddc220af12c2192cfa6eedaca409c34ffa4d5074741d76b7be1"}