{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:HRMZDMELZMFNUSQM2QP63CRZTB","short_pith_number":"pith:HRMZDMEL","canonical_record":{"source":{"id":"2406.14670","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-20T18:47:43Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"afb031116fd6e93848d00b667e7a6f4e873de455ad225315253d593942070c12","abstract_canon_sha256":"9bb30fa1564249fd3287c564b920643461018b5b5a07281842699ad422cd9624"},"schema_version":"1.0"},"canonical_sha256":"3c5991b08bcb0ada4a0cd41fed8a3998789792816c4b24a7e0ffcc518119ae0a","source":{"kind":"arxiv","id":"2406.14670","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.14670","created_at":"2026-07-05T09:28:32Z"},{"alias_kind":"arxiv_version","alias_value":"2406.14670v2","created_at":"2026-07-05T09:28:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.14670","created_at":"2026-07-05T09:28:32Z"},{"alias_kind":"pith_short_12","alias_value":"HRMZDMELZMFN","created_at":"2026-07-05T09:28:32Z"},{"alias_kind":"pith_short_16","alias_value":"HRMZDMELZMFNUSQM","created_at":"2026-07-05T09:28:32Z"},{"alias_kind":"pith_short_8","alias_value":"HRMZDMEL","created_at":"2026-07-05T09:28:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:HRMZDMELZMFNUSQM2QP63CRZTB","target":"record","payload":{"canonical_record":{"source":{"id":"2406.14670","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-20T18:47:43Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"afb031116fd6e93848d00b667e7a6f4e873de455ad225315253d593942070c12","abstract_canon_sha256":"9bb30fa1564249fd3287c564b920643461018b5b5a07281842699ad422cd9624"},"schema_version":"1.0"},"canonical_sha256":"3c5991b08bcb0ada4a0cd41fed8a3998789792816c4b24a7e0ffcc518119ae0a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:32.712840Z","signature_b64":"53Vyar6v7+VyW8fFRRWaIWA5CiEmog64cCcfzU3R6yy0R9Wr6KUorjWAtK1rI2dozc8wfACZpsiVAcL8ypaTAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c5991b08bcb0ada4a0cd41fed8a3998789792816c4b24a7e0ffcc518119ae0a","last_reissued_at":"2026-07-05T09:28:32.712290Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:32.712290Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.14670","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:28:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Yr6oyIjj4ulfRajLqDSvANyRIaVTQ36qwsZqobmEel+DFkdRsQ/YybgOlROLI4P2xmlNimoPXD8EQGB8UQveCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:12:11.335455Z"},"content_sha256":"8a2662b07823c17d6eff2b6279d97d222194a3691e58527278122c99e0e002e4","schema_version":"1.0","event_id":"sha256:8a2662b07823c17d6eff2b6279d97d222194a3691e58527278122c99e0e002e4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:HRMZDMELZMFNUSQM2QP63CRZTB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Exploring Design Choices for Building Language-Specific LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Atula Tejaswi, Eunsol Choi, Nilesh Gupta","submitted_at":"2024-06-20T18:47:43Z","abstract_excerpt":"Despite rapid progress in large language models (LLMs), their performance on a vast majority of languages remains unsatisfactory. In this paper, we study building language-specific LLMs by adapting monolingual and multilingual LLMs. We conduct systematic experiments on how design choices (base model selection, vocabulary extension, and continued pretraining) impact the adapted LLM, both in terms of efficiency (how many tokens are needed to encode the same amount of information) and end task performance. We find that (1) the initial performance of LLM does not always correlate with the final pe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.14670","kind":"arxiv","version":2},"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/2406.14670/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":"2026-07-05T09:28:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7Fv5qQZfe5MF5PymsbsQJJQ4qxbAqxqjEiCYBFOP28fcsw5KR1muGHX1cFsoQPK/kGPxS49IU4ZBnRzUJQEdDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:12:11.335970Z"},"content_sha256":"2a1bec8ac94423083be581f8cb34d81f0a7e5d185e7f29207c21e11c24a16d7e","schema_version":"1.0","event_id":"sha256:2a1bec8ac94423083be581f8cb34d81f0a7e5d185e7f29207c21e11c24a16d7e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HRMZDMELZMFNUSQM2QP63CRZTB/bundle.json","state_url":"https://pith.science/pith/HRMZDMELZMFNUSQM2QP63CRZTB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HRMZDMELZMFNUSQM2QP63CRZTB/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":"2026-08-08T11:12:11Z","links":{"resolver":"https://pith.science/pith/HRMZDMELZMFNUSQM2QP63CRZTB","bundle":"https://pith.science/pith/HRMZDMELZMFNUSQM2QP63CRZTB/bundle.json","state":"https://pith.science/pith/HRMZDMELZMFNUSQM2QP63CRZTB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HRMZDMELZMFNUSQM2QP63CRZTB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HRMZDMELZMFNUSQM2QP63CRZTB","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":"9bb30fa1564249fd3287c564b920643461018b5b5a07281842699ad422cd9624","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-20T18:47:43Z","title_canon_sha256":"afb031116fd6e93848d00b667e7a6f4e873de455ad225315253d593942070c12"},"schema_version":"1.0","source":{"id":"2406.14670","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.14670","created_at":"2026-07-05T09:28:32Z"},{"alias_kind":"arxiv_version","alias_value":"2406.14670v2","created_at":"2026-07-05T09:28:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.14670","created_at":"2026-07-05T09:28:32Z"},{"alias_kind":"pith_short_12","alias_value":"HRMZDMELZMFN","created_at":"2026-07-05T09:28:32Z"},{"alias_kind":"pith_short_16","alias_value":"HRMZDMELZMFNUSQM","created_at":"2026-07-05T09:28:32Z"},{"alias_kind":"pith_short_8","alias_value":"HRMZDMEL","created_at":"2026-07-05T09:28:32Z"}],"graph_snapshots":[{"event_id":"sha256:2a1bec8ac94423083be581f8cb34d81f0a7e5d185e7f29207c21e11c24a16d7e","target":"graph","created_at":"2026-07-05T09:28:32Z","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/2406.14670/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite rapid progress in large language models (LLMs), their performance on a vast majority of languages remains unsatisfactory. In this paper, we study building language-specific LLMs by adapting monolingual and multilingual LLMs. We conduct systematic experiments on how design choices (base model selection, vocabulary extension, and continued pretraining) impact the adapted LLM, both in terms of efficiency (how many tokens are needed to encode the same amount of information) and end task performance. We find that (1) the initial performance of LLM does not always correlate with the final pe","authors_text":"Atula Tejaswi, Eunsol Choi, Nilesh Gupta","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-20T18:47:43Z","title":"Exploring Design Choices for Building Language-Specific LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.14670","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":"sha256:8a2662b07823c17d6eff2b6279d97d222194a3691e58527278122c99e0e002e4","target":"record","created_at":"2026-07-05T09:28:32Z","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":"9bb30fa1564249fd3287c564b920643461018b5b5a07281842699ad422cd9624","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-20T18:47:43Z","title_canon_sha256":"afb031116fd6e93848d00b667e7a6f4e873de455ad225315253d593942070c12"},"schema_version":"1.0","source":{"id":"2406.14670","kind":"arxiv","version":2}},"canonical_sha256":"3c5991b08bcb0ada4a0cd41fed8a3998789792816c4b24a7e0ffcc518119ae0a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3c5991b08bcb0ada4a0cd41fed8a3998789792816c4b24a7e0ffcc518119ae0a","first_computed_at":"2026-07-05T09:28:32.712290Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:28:32.712290Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"53Vyar6v7+VyW8fFRRWaIWA5CiEmog64cCcfzU3R6yy0R9Wr6KUorjWAtK1rI2dozc8wfACZpsiVAcL8ypaTAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:28:32.712840Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.14670","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8a2662b07823c17d6eff2b6279d97d222194a3691e58527278122c99e0e002e4","sha256:2a1bec8ac94423083be581f8cb34d81f0a7e5d185e7f29207c21e11c24a16d7e"],"state_sha256":"26e5e21f183dc2114a3f81d51226e9a4572947b6b21ac7ab0fbf5438ebd06abe"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bj8gKgIlerZZqUxwJY7sHEE4PvjUgDksE7AaKjFP8hZpCtzhezYwvE6+jsSuQ4Q2WkdiDFT66+7e7Zd0PQyyCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T11:12:11.341398Z","bundle_sha256":"7e48eceb47cface712f3aa7ac70b085f72e0ad3f35a483ae91f56ffbe1ac4d92"}}