{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:L2XUFX5XBGD6CRU323UNACIRKY","short_pith_number":"pith:L2XUFX5X","canonical_record":{"source":{"id":"2407.16222","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-23T06:59:53Z","cross_cats_sorted":[],"title_canon_sha256":"3153e33a5d93a6ac1f9c400c66a29e2366c8cf974efd3c0d1353f5414dc241f3","abstract_canon_sha256":"9a175e788b951958cfa748407829749c2cb51439dbbe69863788cdb665d87fee"},"schema_version":"1.0"},"canonical_sha256":"5eaf42dfb70987e1469bd6e8d0091156204f501e9d05f5ee9da382241308235f","source":{"kind":"arxiv","id":"2407.16222","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.16222","created_at":"2026-07-05T09:36:13Z"},{"alias_kind":"arxiv_version","alias_value":"2407.16222v3","created_at":"2026-07-05T09:36:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.16222","created_at":"2026-07-05T09:36:13Z"},{"alias_kind":"pith_short_12","alias_value":"L2XUFX5XBGD6","created_at":"2026-07-05T09:36:13Z"},{"alias_kind":"pith_short_16","alias_value":"L2XUFX5XBGD6CRU3","created_at":"2026-07-05T09:36:13Z"},{"alias_kind":"pith_short_8","alias_value":"L2XUFX5X","created_at":"2026-07-05T09:36:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:L2XUFX5XBGD6CRU323UNACIRKY","target":"record","payload":{"canonical_record":{"source":{"id":"2407.16222","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-23T06:59:53Z","cross_cats_sorted":[],"title_canon_sha256":"3153e33a5d93a6ac1f9c400c66a29e2366c8cf974efd3c0d1353f5414dc241f3","abstract_canon_sha256":"9a175e788b951958cfa748407829749c2cb51439dbbe69863788cdb665d87fee"},"schema_version":"1.0"},"canonical_sha256":"5eaf42dfb70987e1469bd6e8d0091156204f501e9d05f5ee9da382241308235f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:36:13.374343Z","signature_b64":"/o98f/EEJN11S8pxTklM7vCG2uKxOib4hI+M/8QP2itXJNPT4pl4YZZ+cfJKdlp4Nmtap9tsG6YtSyZyQp9oCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5eaf42dfb70987e1469bd6e8d0091156204f501e9d05f5ee9da382241308235f","last_reissued_at":"2026-07-05T09:36:13.373846Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:36:13.373846Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.16222","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:36:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9i4zoc4sCQE3OV12n4Jv3DVWLkpHttZK2dNKvD6GQMfCxYnH5uOlRs3cnnELB2LlgrxKQgrf7PEc3Fo0S9zRBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T07:38:12.420552Z"},"content_sha256":"28cd36ebe0f44aa9bc3f2f853cdfd94ba1aba18337112ecbf8361ce317f38c41","schema_version":"1.0","event_id":"sha256:28cd36ebe0f44aa9bc3f2f853cdfd94ba1aba18337112ecbf8361ce317f38c41"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:L2XUFX5XBGD6CRU323UNACIRKY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PreAlign: Boosting Cross-Lingual Transfer by Early Establishment of Multilingual Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aarron Ching, Jiahuan Li, Jiajun Chen, Shujian Huang, Xinyu Dai","submitted_at":"2024-07-23T06:59:53Z","abstract_excerpt":"Large language models demonstrate reasonable multilingual abilities, despite predominantly English-centric pretraining. However, the spontaneous multilingual alignment in these models is shown to be weak, leading to unsatisfactory cross-lingual transfer and knowledge sharing. Previous works attempt to address this issue by explicitly injecting multilingual alignment information during or after pretraining. Thus for the early stage in pretraining, the alignment is weak for sharing information or knowledge across languages. In this paper, we propose PreAlign, a framework that establishes multili"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.16222","kind":"arxiv","version":3},"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/2407.16222/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":"2026-07-05T09:36:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aj7ruODm09x8g3ycjOYBa6d2eT2LK/fpEzDScKwSDnAe0XpASOJgHwU9WIPSdseFthgAd8jVHI8Cl38IzVU2Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T07:38:12.421527Z"},"content_sha256":"700d37bc38e8100563dff8c9fbe4c7a833090937a1f5a47290a7d8286f6e144d","schema_version":"1.0","event_id":"sha256:700d37bc38e8100563dff8c9fbe4c7a833090937a1f5a47290a7d8286f6e144d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/L2XUFX5XBGD6CRU323UNACIRKY/bundle.json","state_url":"https://pith.science/pith/L2XUFX5XBGD6CRU323UNACIRKY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/L2XUFX5XBGD6CRU323UNACIRKY/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":"2026-08-05T07:38:12Z","links":{"resolver":"https://pith.science/pith/L2XUFX5XBGD6CRU323UNACIRKY","bundle":"https://pith.science/pith/L2XUFX5XBGD6CRU323UNACIRKY/bundle.json","state":"https://pith.science/pith/L2XUFX5XBGD6CRU323UNACIRKY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/L2XUFX5XBGD6CRU323UNACIRKY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:L2XUFX5XBGD6CRU323UNACIRKY","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":"9a175e788b951958cfa748407829749c2cb51439dbbe69863788cdb665d87fee","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-23T06:59:53Z","title_canon_sha256":"3153e33a5d93a6ac1f9c400c66a29e2366c8cf974efd3c0d1353f5414dc241f3"},"schema_version":"1.0","source":{"id":"2407.16222","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.16222","created_at":"2026-07-05T09:36:13Z"},{"alias_kind":"arxiv_version","alias_value":"2407.16222v3","created_at":"2026-07-05T09:36:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.16222","created_at":"2026-07-05T09:36:13Z"},{"alias_kind":"pith_short_12","alias_value":"L2XUFX5XBGD6","created_at":"2026-07-05T09:36:13Z"},{"alias_kind":"pith_short_16","alias_value":"L2XUFX5XBGD6CRU3","created_at":"2026-07-05T09:36:13Z"},{"alias_kind":"pith_short_8","alias_value":"L2XUFX5X","created_at":"2026-07-05T09:36:13Z"}],"graph_snapshots":[{"event_id":"sha256:700d37bc38e8100563dff8c9fbe4c7a833090937a1f5a47290a7d8286f6e144d","target":"graph","created_at":"2026-07-05T09:36:13Z","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/2407.16222/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models demonstrate reasonable multilingual abilities, despite predominantly English-centric pretraining. However, the spontaneous multilingual alignment in these models is shown to be weak, leading to unsatisfactory cross-lingual transfer and knowledge sharing. Previous works attempt to address this issue by explicitly injecting multilingual alignment information during or after pretraining. Thus for the early stage in pretraining, the alignment is weak for sharing information or knowledge across languages. In this paper, we propose PreAlign, a framework that establishes multili","authors_text":"Aarron Ching, Jiahuan Li, Jiajun Chen, Shujian Huang, Xinyu Dai","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-23T06:59:53Z","title":"PreAlign: Boosting Cross-Lingual Transfer by Early Establishment of Multilingual Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.16222","kind":"arxiv","version":3},"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":"sha256:28cd36ebe0f44aa9bc3f2f853cdfd94ba1aba18337112ecbf8361ce317f38c41","target":"record","created_at":"2026-07-05T09:36:13Z","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":"9a175e788b951958cfa748407829749c2cb51439dbbe69863788cdb665d87fee","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-23T06:59:53Z","title_canon_sha256":"3153e33a5d93a6ac1f9c400c66a29e2366c8cf974efd3c0d1353f5414dc241f3"},"schema_version":"1.0","source":{"id":"2407.16222","kind":"arxiv","version":3}},"canonical_sha256":"5eaf42dfb70987e1469bd6e8d0091156204f501e9d05f5ee9da382241308235f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5eaf42dfb70987e1469bd6e8d0091156204f501e9d05f5ee9da382241308235f","first_computed_at":"2026-07-05T09:36:13.373846Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:36:13.373846Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/o98f/EEJN11S8pxTklM7vCG2uKxOib4hI+M/8QP2itXJNPT4pl4YZZ+cfJKdlp4Nmtap9tsG6YtSyZyQp9oCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:36:13.374343Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.16222","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:28cd36ebe0f44aa9bc3f2f853cdfd94ba1aba18337112ecbf8361ce317f38c41","sha256:700d37bc38e8100563dff8c9fbe4c7a833090937a1f5a47290a7d8286f6e144d"],"state_sha256":"53702d1e8622c5104a7d5561d05d2013314af46cc2ca9a137b341aa8d3908a8b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UFL/rkMwc+nAxu1DAsKU9wqT2Eaw2Hg048ngjq90sjoL/hyihQ8lk8HW/1NE+WggOKQFjbPrzRCXTJI4A8sSAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T07:38:12.428419Z","bundle_sha256":"4039610770b36acae29f4fe785f4e895ab616e51bad6096fa1b932d095ce655b"}}