{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:YEQBCKEWQ76BVF3MT477Z6WEOC","short_pith_number":"pith:YEQBCKEW","canonical_record":{"source":{"id":"2502.08037","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-12T00:38:11Z","cross_cats_sorted":[],"title_canon_sha256":"f9149e8fc41e3ad821b280ba82305633d2386f5c6c47efeafc1e2f218d8cd6ec","abstract_canon_sha256":"fbdf905e586bde9aa30addee460311445fb25409d9dc557a58a8e56d2ad92e07"},"schema_version":"1.0"},"canonical_sha256":"c12011289687fc1a976c9f3ffcfac4709a96535ffa484510a5e2451c69946edb","source":{"kind":"arxiv","id":"2502.08037","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.08037","created_at":"2026-07-05T10:13:14Z"},{"alias_kind":"arxiv_version","alias_value":"2502.08037v1","created_at":"2026-07-05T10:13:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.08037","created_at":"2026-07-05T10:13:14Z"},{"alias_kind":"pith_short_12","alias_value":"YEQBCKEWQ76B","created_at":"2026-07-05T10:13:14Z"},{"alias_kind":"pith_short_16","alias_value":"YEQBCKEWQ76BVF3M","created_at":"2026-07-05T10:13:14Z"},{"alias_kind":"pith_short_8","alias_value":"YEQBCKEW","created_at":"2026-07-05T10:13:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:YEQBCKEWQ76BVF3MT477Z6WEOC","target":"record","payload":{"canonical_record":{"source":{"id":"2502.08037","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-12T00:38:11Z","cross_cats_sorted":[],"title_canon_sha256":"f9149e8fc41e3ad821b280ba82305633d2386f5c6c47efeafc1e2f218d8cd6ec","abstract_canon_sha256":"fbdf905e586bde9aa30addee460311445fb25409d9dc557a58a8e56d2ad92e07"},"schema_version":"1.0"},"canonical_sha256":"c12011289687fc1a976c9f3ffcfac4709a96535ffa484510a5e2451c69946edb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:13:14.215020Z","signature_b64":"PMZmnmGTFyUBpehtw6UmnhBvQiAkTlXjLWNqbEbBjOgQDF1y7LXPnLvv2Fg2UJQDzaejCx7A9+6tKOK+XMXACQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c12011289687fc1a976c9f3ffcfac4709a96535ffa484510a5e2451c69946edb","last_reissued_at":"2026-07-05T10:13:14.214486Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:13:14.214486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.08037","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":"2026-07-05T10:13:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G0V3vjTNuo70CTFXRXgsDHsWfUHihRi8d2UHmRXTLIhBRso4oCD7jAhw2CTl6v8V3SeV0u5ZeFouEIBADakKAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T06:53:01.343207Z"},"content_sha256":"5e0f9755350656b6b0ea2ea59c9bce7c23b9e2168985cdadae8598fe178d4df2","schema_version":"1.0","event_id":"sha256:5e0f9755350656b6b0ea2ea59c9bce7c23b9e2168985cdadae8598fe178d4df2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:YEQBCKEWQ76BVF3MT477Z6WEOC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Franken-Adapter: Cross-Lingual Adaptation of LLMs by Embedding Surgery","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fan Jiang, Grace Chung, Honglin Yu, Trevor Cohn","submitted_at":"2025-02-12T00:38:11Z","abstract_excerpt":"The capabilities of Large Language Models (LLMs) in low-resource languages lag far behind those in English, making their universal accessibility a significant challenge. To alleviate this, we present $\\textit{Franken-Adapter}$, a modular language adaptation approach for decoder-only LLMs with embedding surgery. Our method begins by creating customized vocabularies for target languages and performing language adaptation through embedding tuning on multilingual data. These pre-trained embeddings are subsequently integrated with LLMs that have been instruction-tuned on English alignment data to e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.08037","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/2502.08037/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":"2026-07-05T10:13:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HL31pK7PvNt3a+3rL8YmiZ0nW+9hkUfVdgGWJ1fj2IMDYedW8fuNf2tplOQ6wLycPqlQDm/jix2yaG3WZOQnCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T06:53:01.343920Z"},"content_sha256":"21cfd43f976dd0e68a0af0a9edbc9baaf997f9d73281fb8f73112191b54f688f","schema_version":"1.0","event_id":"sha256:21cfd43f976dd0e68a0af0a9edbc9baaf997f9d73281fb8f73112191b54f688f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YEQBCKEWQ76BVF3MT477Z6WEOC/bundle.json","state_url":"https://pith.science/pith/YEQBCKEWQ76BVF3MT477Z6WEOC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YEQBCKEWQ76BVF3MT477Z6WEOC/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":"2026-08-09T06:53:01Z","links":{"resolver":"https://pith.science/pith/YEQBCKEWQ76BVF3MT477Z6WEOC","bundle":"https://pith.science/pith/YEQBCKEWQ76BVF3MT477Z6WEOC/bundle.json","state":"https://pith.science/pith/YEQBCKEWQ76BVF3MT477Z6WEOC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YEQBCKEWQ76BVF3MT477Z6WEOC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YEQBCKEWQ76BVF3MT477Z6WEOC","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":"fbdf905e586bde9aa30addee460311445fb25409d9dc557a58a8e56d2ad92e07","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-12T00:38:11Z","title_canon_sha256":"f9149e8fc41e3ad821b280ba82305633d2386f5c6c47efeafc1e2f218d8cd6ec"},"schema_version":"1.0","source":{"id":"2502.08037","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.08037","created_at":"2026-07-05T10:13:14Z"},{"alias_kind":"arxiv_version","alias_value":"2502.08037v1","created_at":"2026-07-05T10:13:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.08037","created_at":"2026-07-05T10:13:14Z"},{"alias_kind":"pith_short_12","alias_value":"YEQBCKEWQ76B","created_at":"2026-07-05T10:13:14Z"},{"alias_kind":"pith_short_16","alias_value":"YEQBCKEWQ76BVF3M","created_at":"2026-07-05T10:13:14Z"},{"alias_kind":"pith_short_8","alias_value":"YEQBCKEW","created_at":"2026-07-05T10:13:14Z"}],"graph_snapshots":[{"event_id":"sha256:21cfd43f976dd0e68a0af0a9edbc9baaf997f9d73281fb8f73112191b54f688f","target":"graph","created_at":"2026-07-05T10:13:14Z","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/2502.08037/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The capabilities of Large Language Models (LLMs) in low-resource languages lag far behind those in English, making their universal accessibility a significant challenge. To alleviate this, we present $\\textit{Franken-Adapter}$, a modular language adaptation approach for decoder-only LLMs with embedding surgery. Our method begins by creating customized vocabularies for target languages and performing language adaptation through embedding tuning on multilingual data. These pre-trained embeddings are subsequently integrated with LLMs that have been instruction-tuned on English alignment data to e","authors_text":"Fan Jiang, Grace Chung, Honglin Yu, Trevor Cohn","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-12T00:38:11Z","title":"Franken-Adapter: Cross-Lingual Adaptation of LLMs by Embedding Surgery"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.08037","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":"sha256:5e0f9755350656b6b0ea2ea59c9bce7c23b9e2168985cdadae8598fe178d4df2","target":"record","created_at":"2026-07-05T10:13:14Z","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":"fbdf905e586bde9aa30addee460311445fb25409d9dc557a58a8e56d2ad92e07","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-12T00:38:11Z","title_canon_sha256":"f9149e8fc41e3ad821b280ba82305633d2386f5c6c47efeafc1e2f218d8cd6ec"},"schema_version":"1.0","source":{"id":"2502.08037","kind":"arxiv","version":1}},"canonical_sha256":"c12011289687fc1a976c9f3ffcfac4709a96535ffa484510a5e2451c69946edb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c12011289687fc1a976c9f3ffcfac4709a96535ffa484510a5e2451c69946edb","first_computed_at":"2026-07-05T10:13:14.214486Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:13:14.214486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PMZmnmGTFyUBpehtw6UmnhBvQiAkTlXjLWNqbEbBjOgQDF1y7LXPnLvv2Fg2UJQDzaejCx7A9+6tKOK+XMXACQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:13:14.215020Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.08037","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5e0f9755350656b6b0ea2ea59c9bce7c23b9e2168985cdadae8598fe178d4df2","sha256:21cfd43f976dd0e68a0af0a9edbc9baaf997f9d73281fb8f73112191b54f688f"],"state_sha256":"077ad1a4ade9919dc87745cc3168e845908a64ed9535d49218eb60f1c841506e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xrNh/3612f4vVWvKhDUbzKsq5c/4EV99p9V+gOoRwhO/LzPMRJZfXMcHaSXyvmF9d+xcXjeGUfiODUN0K0u5Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T06:53:01.349165Z","bundle_sha256":"3483d4eb6aaaa097df86ca04ff3b9c894d62965b6bda35a1f4dee1629a5a1cff"}}