{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ORMZXKCRTDBGL5TP5TNJZMQAEC","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":"a24ef04991909f1e1842143c5f7435caa55b0bdc152178b0b211793855803fd9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-10T08:28:57Z","title_canon_sha256":"4528421681fe833202a6372af533c0ff52c96b15838fda9760a76d03501e5a74"},"schema_version":"1.0","source":{"id":"2412.07298","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.07298","created_at":"2026-07-05T10:22:54Z"},{"alias_kind":"arxiv_version","alias_value":"2412.07298v2","created_at":"2026-07-05T10:22:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.07298","created_at":"2026-07-05T10:22:54Z"},{"alias_kind":"pith_short_12","alias_value":"ORMZXKCRTDBG","created_at":"2026-07-05T10:22:54Z"},{"alias_kind":"pith_short_16","alias_value":"ORMZXKCRTDBGL5TP","created_at":"2026-07-05T10:22:54Z"},{"alias_kind":"pith_short_8","alias_value":"ORMZXKCR","created_at":"2026-07-05T10:22:54Z"}],"graph_snapshots":[{"event_id":"sha256:711fb0319fd5083263a0cf490f7491cb3b51dc5d000fd0ee1eadd0b61d8d29f8","target":"graph","created_at":"2026-07-05T10:22:54Z","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/2412.07298/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have shown significant multilingual capabilities. However, the mechanisms underlying the development of these capabilities during pre-training are not well understood. In this paper, we use code LLMs as an experimental platform to explore the evolution of multilingual capabilities in LLMs during the pre-training process. Based on our observations, we propose the Babel Tower Hypothesis, which describes the entire process of LLMs acquiring new language capabilities. During the learning process, multiple languages initially share a single knowledge system dominated by","authors_text":"Hongyu Lin, Jiawei Chen, Jingjing Xu, Jing Su, Le Sun, Mengjie Ren, Wentao Chen, Xianpei Han, Yaojie Lu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-10T08:28:57Z","title":"The Rise and Down of Babel Tower: Investigating the Evolution Process of Multilingual Code Large Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.07298","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":"sha256:80a590bf3441002d7b9439a0c42026fa18754977acdafbd77f0fb58872a3ed76","target":"record","created_at":"2026-07-05T10:22:54Z","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":"a24ef04991909f1e1842143c5f7435caa55b0bdc152178b0b211793855803fd9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-10T08:28:57Z","title_canon_sha256":"4528421681fe833202a6372af533c0ff52c96b15838fda9760a76d03501e5a74"},"schema_version":"1.0","source":{"id":"2412.07298","kind":"arxiv","version":2}},"canonical_sha256":"74599ba85198c265f66fecda9cb200209d98d67c58ff6667998d620882c793e2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"74599ba85198c265f66fecda9cb200209d98d67c58ff6667998d620882c793e2","first_computed_at":"2026-07-05T10:22:54.482084Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:22:54.482084Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"k+9ygPjVR3cLES9wnHEpaXBTxkrWgRS1nVONDdBRls/NzAEusDplApsgQhMiZvcEmG+0j2ujemZMT3s4qLGJDg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:22:54.482786Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.07298","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:80a590bf3441002d7b9439a0c42026fa18754977acdafbd77f0fb58872a3ed76","sha256:711fb0319fd5083263a0cf490f7491cb3b51dc5d000fd0ee1eadd0b61d8d29f8"],"state_sha256":"3940e047cced8b3a077cd16845533ef74aefb084da74614484d2911a818ddc9c"}