{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:B3RNZNUEMQRWAI6J3SXCBIF37R","short_pith_number":"pith:B3RNZNUE","canonical_record":{"source":{"id":"2412.04003","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-05T09:26:58Z","cross_cats_sorted":[],"title_canon_sha256":"d189974e812d08f0c81b7bc40d0070dff052e9451eb25fb476ab50168a86cbe9","abstract_canon_sha256":"9f9b9708f1b3c5ae2cd5cb9fe5c6dde9da6dfd467cfeffba3a42aa05df05db36"},"schema_version":"1.0"},"canonical_sha256":"0ee2dcb68464236023c9dcae20a0bbfc6e6cb9a0b3905cc593c11c0847a09ec2","source":{"kind":"arxiv","id":"2412.04003","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.04003","created_at":"2026-07-05T09:44:57Z"},{"alias_kind":"arxiv_version","alias_value":"2412.04003v1","created_at":"2026-07-05T09:44:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04003","created_at":"2026-07-05T09:44:57Z"},{"alias_kind":"pith_short_12","alias_value":"B3RNZNUEMQRW","created_at":"2026-07-05T09:44:57Z"},{"alias_kind":"pith_short_16","alias_value":"B3RNZNUEMQRWAI6J","created_at":"2026-07-05T09:44:57Z"},{"alias_kind":"pith_short_8","alias_value":"B3RNZNUE","created_at":"2026-07-05T09:44:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:B3RNZNUEMQRWAI6J3SXCBIF37R","target":"record","payload":{"canonical_record":{"source":{"id":"2412.04003","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-05T09:26:58Z","cross_cats_sorted":[],"title_canon_sha256":"d189974e812d08f0c81b7bc40d0070dff052e9451eb25fb476ab50168a86cbe9","abstract_canon_sha256":"9f9b9708f1b3c5ae2cd5cb9fe5c6dde9da6dfd467cfeffba3a42aa05df05db36"},"schema_version":"1.0"},"canonical_sha256":"0ee2dcb68464236023c9dcae20a0bbfc6e6cb9a0b3905cc593c11c0847a09ec2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:44:57.851405Z","signature_b64":"vE00jDBXMgVZiiWSQZhtDXwGeERuKWkNC4qCCSbVixDUS0QZ53uvHKQZitO4c29/xetWJItXqfqq5C5ILUUUCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ee2dcb68464236023c9dcae20a0bbfc6e6cb9a0b3905cc593c11c0847a09ec2","last_reissued_at":"2026-07-05T09:44:57.850931Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:44:57.850931Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.04003","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:44:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pPMMi1WYW8vB2KG4bL3+Ucp4aLkA8+NqapAzpd74+UMFGPEZgZGWHDzGC0EhtZuEibj5hkxYe8M0MJLjcLOtBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T13:31:49.249885Z"},"content_sha256":"6d7acb042153fbe17a1b6baf2e66a8e4bd77cf9a1ae8a2f022801f4c8c67b44d","schema_version":"1.0","event_id":"sha256:6d7acb042153fbe17a1b6baf2e66a8e4bd77cf9a1ae8a2f022801f4c8c67b44d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:B3RNZNUEMQRWAI6J3SXCBIF37R","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Marco-LLM: Bridging Languages via Massive Multilingual Training for Cross-Lingual Enhancement","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bo Zeng, Chenyang Lyu, Haijun Li, Hao Wang, Hao Zhou, Heng Liu, Huifeng Yin, Kaifu Zhang, Lingfeng Ming, Linlong Xu, Longyue Wang, Tianqi Shi, Weihua Luo, Xiaohu Zhao, Xue Yang, Yangyang Liu, Yefeng Liu, Yiyu Wang, Yu Zhao, Zifu Shang","submitted_at":"2024-12-05T09:26:58Z","abstract_excerpt":"Large Language Models (LLMs) have achieved remarkable progress in recent years; however, their excellent performance is still largely limited to major world languages, primarily English. Many LLMs continue to face challenges with multilingual tasks, especially when it comes to low-resource languages. To address this issue, we introduced Marco-LLM: Massive multilingual training for cross-lingual enhancement LLM. We have collected a substantial amount of multilingual data for several low-resource languages and conducted extensive continual pre-training using the Qwen2 models. This effort has res"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04003","kind":"arxiv","version":1},"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/2412.04003/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":"2026-07-05T09:44:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y87DhtcJdIQipAlqriZr1YNq20iYvHXKPep0SOCpq30SdyGCs7EXes4Zjr58t/d8Lo0FoxW5bLf8DTjr2ZtCBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T13:31:49.250456Z"},"content_sha256":"584c18359c28065abf02966da117dd5cb67ad9098c2b5b2d6dd1aaf36fd836dd","schema_version":"1.0","event_id":"sha256:584c18359c28065abf02966da117dd5cb67ad9098c2b5b2d6dd1aaf36fd836dd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/B3RNZNUEMQRWAI6J3SXCBIF37R/bundle.json","state_url":"https://pith.science/pith/B3RNZNUEMQRWAI6J3SXCBIF37R/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/B3RNZNUEMQRWAI6J3SXCBIF37R/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":"2026-08-14T13:31:49Z","links":{"resolver":"https://pith.science/pith/B3RNZNUEMQRWAI6J3SXCBIF37R","bundle":"https://pith.science/pith/B3RNZNUEMQRWAI6J3SXCBIF37R/bundle.json","state":"https://pith.science/pith/B3RNZNUEMQRWAI6J3SXCBIF37R/state.json","well_known_bundle":"https://pith.science/.well-known/pith/B3RNZNUEMQRWAI6J3SXCBIF37R/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:B3RNZNUEMQRWAI6J3SXCBIF37R","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":"9f9b9708f1b3c5ae2cd5cb9fe5c6dde9da6dfd467cfeffba3a42aa05df05db36","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-05T09:26:58Z","title_canon_sha256":"d189974e812d08f0c81b7bc40d0070dff052e9451eb25fb476ab50168a86cbe9"},"schema_version":"1.0","source":{"id":"2412.04003","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.04003","created_at":"2026-07-05T09:44:57Z"},{"alias_kind":"arxiv_version","alias_value":"2412.04003v1","created_at":"2026-07-05T09:44:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04003","created_at":"2026-07-05T09:44:57Z"},{"alias_kind":"pith_short_12","alias_value":"B3RNZNUEMQRW","created_at":"2026-07-05T09:44:57Z"},{"alias_kind":"pith_short_16","alias_value":"B3RNZNUEMQRWAI6J","created_at":"2026-07-05T09:44:57Z"},{"alias_kind":"pith_short_8","alias_value":"B3RNZNUE","created_at":"2026-07-05T09:44:57Z"}],"graph_snapshots":[{"event_id":"sha256:584c18359c28065abf02966da117dd5cb67ad9098c2b5b2d6dd1aaf36fd836dd","target":"graph","created_at":"2026-07-05T09:44:57Z","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/2412.04003/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have achieved remarkable progress in recent years; however, their excellent performance is still largely limited to major world languages, primarily English. Many LLMs continue to face challenges with multilingual tasks, especially when it comes to low-resource languages. To address this issue, we introduced Marco-LLM: Massive multilingual training for cross-lingual enhancement LLM. We have collected a substantial amount of multilingual data for several low-resource languages and conducted extensive continual pre-training using the Qwen2 models. This effort has res","authors_text":"Bo Zeng, Chenyang Lyu, Haijun Li, Hao Wang, Hao Zhou, Heng Liu, Huifeng Yin, Kaifu Zhang, Lingfeng Ming, Linlong Xu, Longyue Wang, Tianqi Shi, Weihua Luo, Xiaohu Zhao, Xue Yang, Yangyang Liu, Yefeng Liu, Yiyu Wang, Yu Zhao, Zifu Shang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-05T09:26:58Z","title":"Marco-LLM: Bridging Languages via Massive Multilingual Training for Cross-Lingual Enhancement"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04003","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":"sha256:6d7acb042153fbe17a1b6baf2e66a8e4bd77cf9a1ae8a2f022801f4c8c67b44d","target":"record","created_at":"2026-07-05T09:44:57Z","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":"9f9b9708f1b3c5ae2cd5cb9fe5c6dde9da6dfd467cfeffba3a42aa05df05db36","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-05T09:26:58Z","title_canon_sha256":"d189974e812d08f0c81b7bc40d0070dff052e9451eb25fb476ab50168a86cbe9"},"schema_version":"1.0","source":{"id":"2412.04003","kind":"arxiv","version":1}},"canonical_sha256":"0ee2dcb68464236023c9dcae20a0bbfc6e6cb9a0b3905cc593c11c0847a09ec2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0ee2dcb68464236023c9dcae20a0bbfc6e6cb9a0b3905cc593c11c0847a09ec2","first_computed_at":"2026-07-05T09:44:57.850931Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:44:57.850931Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vE00jDBXMgVZiiWSQZhtDXwGeERuKWkNC4qCCSbVixDUS0QZ53uvHKQZitO4c29/xetWJItXqfqq5C5ILUUUCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:44:57.851405Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.04003","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6d7acb042153fbe17a1b6baf2e66a8e4bd77cf9a1ae8a2f022801f4c8c67b44d","sha256:584c18359c28065abf02966da117dd5cb67ad9098c2b5b2d6dd1aaf36fd836dd"],"state_sha256":"a105c08299151b173f5791281a2e20d347038c4064ac4b7e831ed1b24e98ec53"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"69URn+ZwkSa1XzqGSgbFFZ9r8KlFKuP3tJlfC2SEcM+EJYT6eY0Q1sVSphPdH+Geym6whnFrZd0tkYqfi0RWBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T13:31:49.257560Z","bundle_sha256":"3ee0f1c7faf06e41a2afb1cd49a51eb2eec5b81c9d6a8cd933fbb33479f64594"}}