{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:BY5D5WVDTAYPXXVFUFA45Y27QT","short_pith_number":"pith:BY5D5WVD","canonical_record":{"source":{"id":"2504.01801","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-02T15:09:58Z","cross_cats_sorted":[],"title_canon_sha256":"9efaf846901979f4f85485ea3a716840687766f6356c7f8b985674d71febff3f","abstract_canon_sha256":"cb9aef835e1f443b62e25ae842e5ebbf15a57b6a8ee60239496972180e1f3b5b"},"schema_version":"1.0"},"canonical_sha256":"0e3a3edaa39830fbdea5a141cee35f84e483cfdb4a12a10e2d9635d6136327b4","source":{"kind":"arxiv","id":"2504.01801","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.01801","created_at":"2026-07-05T10:52:21Z"},{"alias_kind":"arxiv_version","alias_value":"2504.01801v2","created_at":"2026-07-05T10:52:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.01801","created_at":"2026-07-05T10:52:21Z"},{"alias_kind":"pith_short_12","alias_value":"BY5D5WVDTAYP","created_at":"2026-07-05T10:52:21Z"},{"alias_kind":"pith_short_16","alias_value":"BY5D5WVDTAYPXXVF","created_at":"2026-07-05T10:52:21Z"},{"alias_kind":"pith_short_8","alias_value":"BY5D5WVD","created_at":"2026-07-05T10:52:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:BY5D5WVDTAYPXXVFUFA45Y27QT","target":"record","payload":{"canonical_record":{"source":{"id":"2504.01801","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-02T15:09:58Z","cross_cats_sorted":[],"title_canon_sha256":"9efaf846901979f4f85485ea3a716840687766f6356c7f8b985674d71febff3f","abstract_canon_sha256":"cb9aef835e1f443b62e25ae842e5ebbf15a57b6a8ee60239496972180e1f3b5b"},"schema_version":"1.0"},"canonical_sha256":"0e3a3edaa39830fbdea5a141cee35f84e483cfdb4a12a10e2d9635d6136327b4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:52:21.693400Z","signature_b64":"kkixvAwnW+HJ+dqraFxNS7rOttRTQPlkytvG3AcNAPTK+T0McEhlaulvV07Ztm/i29oQlLl3ZWvP5EKJuQIrCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e3a3edaa39830fbdea5a141cee35f84e483cfdb4a12a10e2d9635d6136327b4","last_reissued_at":"2026-07-05T10:52:21.692925Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:52:21.692925Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.01801","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":"2026-07-05T10:52:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nYxPuM/9yjzSC2omc3N2cLDX76ADb9uSrtvbMNagWnedhrnfHdO2/77A4QluJK9XRTdKYyfiqK2EZVoehgUMAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T09:21:23.373452Z"},"content_sha256":"3ab1228570cb27ac4be9a5edc5ffeef20e4538fbac684dffcb12ecc70b06c81d","schema_version":"1.0","event_id":"sha256:3ab1228570cb27ac4be9a5edc5ffeef20e4538fbac684dffcb12ecc70b06c81d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:BY5D5WVDTAYPXXVFUFA45Y27QT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Investigating and Scaling up Code-Switching for Multilingual Language Model Pre-Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chao Deng, Hao Zhou, Jiahuan Li, Jingang Wang, Junlan Feng, Rongxiang Weng, Shujian Huang, Xin Huang, Xue Han, Zhijun Wang","submitted_at":"2025-04-02T15:09:58Z","abstract_excerpt":"Large language models (LLMs) exhibit remarkable multilingual capabilities despite the extreme language imbalance in the pre-training data. In this paper, we closely examine the reasons behind this phenomenon, focusing on the pre-training corpus. We find that the existence of code-switching, alternating between different languages within a context, is key to multilingual capabilities. We conduct an analysis to investigate code-switching in the pre-training corpus, examining its presence and categorizing it into four types within two quadrants. We then assess its impact on multilingual performan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.01801","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/2504.01801/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":"2026-07-05T10:52:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1ns8IhwFeJWgC1q8L7WNwMS8DCJZQbRizzJBxOlGBhER4s+vlisASWW5IQp/jJ8uZ2sbwz4eWuGmYkRTJ7XHDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T09:21:23.374529Z"},"content_sha256":"c51aa0ebd83e56d86fc602642ec2e3430c55cead6c02d5b09b01864d47e5e7c3","schema_version":"1.0","event_id":"sha256:c51aa0ebd83e56d86fc602642ec2e3430c55cead6c02d5b09b01864d47e5e7c3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BY5D5WVDTAYPXXVFUFA45Y27QT/bundle.json","state_url":"https://pith.science/pith/BY5D5WVDTAYPXXVFUFA45Y27QT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BY5D5WVDTAYPXXVFUFA45Y27QT/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":"2026-08-06T09:21:23Z","links":{"resolver":"https://pith.science/pith/BY5D5WVDTAYPXXVFUFA45Y27QT","bundle":"https://pith.science/pith/BY5D5WVDTAYPXXVFUFA45Y27QT/bundle.json","state":"https://pith.science/pith/BY5D5WVDTAYPXXVFUFA45Y27QT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BY5D5WVDTAYPXXVFUFA45Y27QT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BY5D5WVDTAYPXXVFUFA45Y27QT","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":"cb9aef835e1f443b62e25ae842e5ebbf15a57b6a8ee60239496972180e1f3b5b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-02T15:09:58Z","title_canon_sha256":"9efaf846901979f4f85485ea3a716840687766f6356c7f8b985674d71febff3f"},"schema_version":"1.0","source":{"id":"2504.01801","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.01801","created_at":"2026-07-05T10:52:21Z"},{"alias_kind":"arxiv_version","alias_value":"2504.01801v2","created_at":"2026-07-05T10:52:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.01801","created_at":"2026-07-05T10:52:21Z"},{"alias_kind":"pith_short_12","alias_value":"BY5D5WVDTAYP","created_at":"2026-07-05T10:52:21Z"},{"alias_kind":"pith_short_16","alias_value":"BY5D5WVDTAYPXXVF","created_at":"2026-07-05T10:52:21Z"},{"alias_kind":"pith_short_8","alias_value":"BY5D5WVD","created_at":"2026-07-05T10:52:21Z"}],"graph_snapshots":[{"event_id":"sha256:c51aa0ebd83e56d86fc602642ec2e3430c55cead6c02d5b09b01864d47e5e7c3","target":"graph","created_at":"2026-07-05T10:52:21Z","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/2504.01801/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) exhibit remarkable multilingual capabilities despite the extreme language imbalance in the pre-training data. In this paper, we closely examine the reasons behind this phenomenon, focusing on the pre-training corpus. We find that the existence of code-switching, alternating between different languages within a context, is key to multilingual capabilities. We conduct an analysis to investigate code-switching in the pre-training corpus, examining its presence and categorizing it into four types within two quadrants. We then assess its impact on multilingual performan","authors_text":"Chao Deng, Hao Zhou, Jiahuan Li, Jingang Wang, Junlan Feng, Rongxiang Weng, Shujian Huang, Xin Huang, Xue Han, Zhijun Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-02T15:09:58Z","title":"Investigating and Scaling up Code-Switching for Multilingual Language Model Pre-Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.01801","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":"sha256:3ab1228570cb27ac4be9a5edc5ffeef20e4538fbac684dffcb12ecc70b06c81d","target":"record","created_at":"2026-07-05T10:52:21Z","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":"cb9aef835e1f443b62e25ae842e5ebbf15a57b6a8ee60239496972180e1f3b5b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-02T15:09:58Z","title_canon_sha256":"9efaf846901979f4f85485ea3a716840687766f6356c7f8b985674d71febff3f"},"schema_version":"1.0","source":{"id":"2504.01801","kind":"arxiv","version":2}},"canonical_sha256":"0e3a3edaa39830fbdea5a141cee35f84e483cfdb4a12a10e2d9635d6136327b4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0e3a3edaa39830fbdea5a141cee35f84e483cfdb4a12a10e2d9635d6136327b4","first_computed_at":"2026-07-05T10:52:21.692925Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:52:21.692925Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kkixvAwnW+HJ+dqraFxNS7rOttRTQPlkytvG3AcNAPTK+T0McEhlaulvV07Ztm/i29oQlLl3ZWvP5EKJuQIrCA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:52:21.693400Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.01801","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3ab1228570cb27ac4be9a5edc5ffeef20e4538fbac684dffcb12ecc70b06c81d","sha256:c51aa0ebd83e56d86fc602642ec2e3430c55cead6c02d5b09b01864d47e5e7c3"],"state_sha256":"b08c92c6391858197cb7847bc832c731d4f32a0dd4e6e1263eeb6f114c1cff7a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xbt4c5h3s5tQ4O/071cBM0d9YhYF0O/sPZNX8nklrgA1KKZH4po3hceGOlqQO2BoWbEviL1cM7HCxnWvlzH/Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T09:21:23.382985Z","bundle_sha256":"d8fd11e3b8d4153952b3dfe7a19e73ae956e034f65625c4eb60c392a2cac4137"}}