{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:2SJQLOXTP4XFTV626NR6Q3MEZK","short_pith_number":"pith:2SJQLOXT","canonical_record":{"source":{"id":"2411.11072","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-17T13:21:26Z","cross_cats_sorted":[],"title_canon_sha256":"754bb8edf7e7f6416d9bd3875c44c37ef9ea0d8e4c259ba94cfce8dc06b5b486","abstract_canon_sha256":"c581437db1c7724a5c812cf984dbff80d9aebe20ec2de8460ef449fd8a74f30e"},"schema_version":"1.0"},"canonical_sha256":"d49305baf37f2e59d7daf363e86d84ca898a186072b75c793b16032631135afc","source":{"kind":"arxiv","id":"2411.11072","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.11072","created_at":"2026-07-05T09:37:12Z"},{"alias_kind":"arxiv_version","alias_value":"2411.11072v2","created_at":"2026-07-05T09:37:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.11072","created_at":"2026-07-05T09:37:12Z"},{"alias_kind":"pith_short_12","alias_value":"2SJQLOXTP4XF","created_at":"2026-07-05T09:37:12Z"},{"alias_kind":"pith_short_16","alias_value":"2SJQLOXTP4XFTV62","created_at":"2026-07-05T09:37:12Z"},{"alias_kind":"pith_short_8","alias_value":"2SJQLOXT","created_at":"2026-07-05T09:37:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:2SJQLOXTP4XFTV626NR6Q3MEZK","target":"record","payload":{"canonical_record":{"source":{"id":"2411.11072","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-17T13:21:26Z","cross_cats_sorted":[],"title_canon_sha256":"754bb8edf7e7f6416d9bd3875c44c37ef9ea0d8e4c259ba94cfce8dc06b5b486","abstract_canon_sha256":"c581437db1c7724a5c812cf984dbff80d9aebe20ec2de8460ef449fd8a74f30e"},"schema_version":"1.0"},"canonical_sha256":"d49305baf37f2e59d7daf363e86d84ca898a186072b75c793b16032631135afc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:37:12.177557Z","signature_b64":"/O/A31zeCcBd9zS204QtRUgnZiJVZQZCtfMK7t0cdwgOkNzLTcl0EcLmK6cfwmfRmtzuGI2QEkgIhA31OXHWDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d49305baf37f2e59d7daf363e86d84ca898a186072b75c793b16032631135afc","last_reissued_at":"2026-07-05T09:37:12.177102Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:37:12.177102Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.11072","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":"2026-07-05T09:37:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+7W64D8wDLyZO+uUi1NRlJVsxZT0SYXKhv+hg2sD/qBe4yRrmCiP24sfHEaA/TEx8vptp1lnQRweXkjF9eDTBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T12:40:46.286708Z"},"content_sha256":"bbbe859109512bb81e73cc700e1c55dc4ef70a1742ea949024ec0b264692eabe","schema_version":"1.0","event_id":"sha256:bbbe859109512bb81e73cc700e1c55dc4ef70a1742ea949024ec0b264692eabe"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:2SJQLOXTP4XFTV626NR6Q3MEZK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multilingual Large Language Models: A Systematic Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ant\\'onio Branco, Deyi Xiong, Haoran Sun, Jiangcun Du, Leiyu Pan, Menglong Cui, Renren Jin, Shaolin Zhu, Shaoyang Xu, Supryadi","submitted_at":"2024-11-17T13:21:26Z","abstract_excerpt":"This paper provides a comprehensive survey of the latest research on multilingual large language models (MLLMs). MLLMs not only are able to understand and generate language across linguistic boundaries, but also represent an important advancement in artificial intelligence. We first discuss the architecture and pre-training objectives of MLLMs, highlighting the key components and methodologies that contribute to their multilingual capabilities. We then discuss the construction of multilingual pre-training and alignment datasets, underscoring the importance of data quality and diversity in enha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.11072","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/2411.11072/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":"2026-07-05T09:37:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hReq6ORpb9lKhPdN7MENzjmLrs9grEO7wUfFyi5N3HR5aXec2sXSgxztnZanQl2iVMMv4z/HV0KKJQwrfH8/Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T12:40:46.287211Z"},"content_sha256":"7794160b07f5f5de05d8244bc914fe25d12271cffe2b8e960695ef6eeb9b0dda","schema_version":"1.0","event_id":"sha256:7794160b07f5f5de05d8244bc914fe25d12271cffe2b8e960695ef6eeb9b0dda"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2SJQLOXTP4XFTV626NR6Q3MEZK/bundle.json","state_url":"https://pith.science/pith/2SJQLOXTP4XFTV626NR6Q3MEZK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2SJQLOXTP4XFTV626NR6Q3MEZK/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":"2026-08-07T12:40:46Z","links":{"resolver":"https://pith.science/pith/2SJQLOXTP4XFTV626NR6Q3MEZK","bundle":"https://pith.science/pith/2SJQLOXTP4XFTV626NR6Q3MEZK/bundle.json","state":"https://pith.science/pith/2SJQLOXTP4XFTV626NR6Q3MEZK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2SJQLOXTP4XFTV626NR6Q3MEZK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2SJQLOXTP4XFTV626NR6Q3MEZK","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":"c581437db1c7724a5c812cf984dbff80d9aebe20ec2de8460ef449fd8a74f30e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-17T13:21:26Z","title_canon_sha256":"754bb8edf7e7f6416d9bd3875c44c37ef9ea0d8e4c259ba94cfce8dc06b5b486"},"schema_version":"1.0","source":{"id":"2411.11072","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.11072","created_at":"2026-07-05T09:37:12Z"},{"alias_kind":"arxiv_version","alias_value":"2411.11072v2","created_at":"2026-07-05T09:37:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.11072","created_at":"2026-07-05T09:37:12Z"},{"alias_kind":"pith_short_12","alias_value":"2SJQLOXTP4XF","created_at":"2026-07-05T09:37:12Z"},{"alias_kind":"pith_short_16","alias_value":"2SJQLOXTP4XFTV62","created_at":"2026-07-05T09:37:12Z"},{"alias_kind":"pith_short_8","alias_value":"2SJQLOXT","created_at":"2026-07-05T09:37:12Z"}],"graph_snapshots":[{"event_id":"sha256:7794160b07f5f5de05d8244bc914fe25d12271cffe2b8e960695ef6eeb9b0dda","target":"graph","created_at":"2026-07-05T09:37:12Z","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/2411.11072/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper provides a comprehensive survey of the latest research on multilingual large language models (MLLMs). MLLMs not only are able to understand and generate language across linguistic boundaries, but also represent an important advancement in artificial intelligence. We first discuss the architecture and pre-training objectives of MLLMs, highlighting the key components and methodologies that contribute to their multilingual capabilities. We then discuss the construction of multilingual pre-training and alignment datasets, underscoring the importance of data quality and diversity in enha","authors_text":"Ant\\'onio Branco, Deyi Xiong, Haoran Sun, Jiangcun Du, Leiyu Pan, Menglong Cui, Renren Jin, Shaolin Zhu, Shaoyang Xu, Supryadi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-17T13:21:26Z","title":"Multilingual Large Language Models: A Systematic Survey"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.11072","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:bbbe859109512bb81e73cc700e1c55dc4ef70a1742ea949024ec0b264692eabe","target":"record","created_at":"2026-07-05T09:37:12Z","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":"c581437db1c7724a5c812cf984dbff80d9aebe20ec2de8460ef449fd8a74f30e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-17T13:21:26Z","title_canon_sha256":"754bb8edf7e7f6416d9bd3875c44c37ef9ea0d8e4c259ba94cfce8dc06b5b486"},"schema_version":"1.0","source":{"id":"2411.11072","kind":"arxiv","version":2}},"canonical_sha256":"d49305baf37f2e59d7daf363e86d84ca898a186072b75c793b16032631135afc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d49305baf37f2e59d7daf363e86d84ca898a186072b75c793b16032631135afc","first_computed_at":"2026-07-05T09:37:12.177102Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:37:12.177102Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/O/A31zeCcBd9zS204QtRUgnZiJVZQZCtfMK7t0cdwgOkNzLTcl0EcLmK6cfwmfRmtzuGI2QEkgIhA31OXHWDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:37:12.177557Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.11072","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bbbe859109512bb81e73cc700e1c55dc4ef70a1742ea949024ec0b264692eabe","sha256:7794160b07f5f5de05d8244bc914fe25d12271cffe2b8e960695ef6eeb9b0dda"],"state_sha256":"59dd4e519768779c40bdc1b73a5a7a1bdc9b9e838a226550a5c227d49c94d010"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9gkUHzAfk+4cw575lMdOhbnanmJbvc4vtDYpmdMqSvRJekl0hTJ0vx74yvDDXM5zLvZ34rp5HagB/f73kDIMBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T12:40:46.292392Z","bundle_sha256":"427a922b84e9b74d557b2b8d58bbbcfa087636d85479de2169508aab339fd426"}}