{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:F7JAJKRD5LQFUHVYCUVHRQ4ZYZ","short_pith_number":"pith:F7JAJKRD","canonical_record":{"source":{"id":"2504.21018","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-21T19:40:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d708f05e8a83a29ec5f5ffaa182a1a0b81afa3c24503cb9912ac26b9dbd59fb8","abstract_canon_sha256":"f207d99e0e33d742389758daa5467c91b12c914a47efa337832b2fcfbf1528f6"},"schema_version":"1.0"},"canonical_sha256":"2fd204aa23eae05a1eb8152a78c399c6404e878645b6abb98b2f53b39a067fc2","source":{"kind":"arxiv","id":"2504.21018","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.21018","created_at":"2026-07-05T11:35:55Z"},{"alias_kind":"arxiv_version","alias_value":"2504.21018v2","created_at":"2026-07-05T11:35:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.21018","created_at":"2026-07-05T11:35:55Z"},{"alias_kind":"pith_short_12","alias_value":"F7JAJKRD5LQF","created_at":"2026-07-05T11:35:55Z"},{"alias_kind":"pith_short_16","alias_value":"F7JAJKRD5LQFUHVY","created_at":"2026-07-05T11:35:55Z"},{"alias_kind":"pith_short_8","alias_value":"F7JAJKRD","created_at":"2026-07-05T11:35:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:F7JAJKRD5LQFUHVYCUVHRQ4ZYZ","target":"record","payload":{"canonical_record":{"source":{"id":"2504.21018","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-21T19:40:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d708f05e8a83a29ec5f5ffaa182a1a0b81afa3c24503cb9912ac26b9dbd59fb8","abstract_canon_sha256":"f207d99e0e33d742389758daa5467c91b12c914a47efa337832b2fcfbf1528f6"},"schema_version":"1.0"},"canonical_sha256":"2fd204aa23eae05a1eb8152a78c399c6404e878645b6abb98b2f53b39a067fc2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:35:55.533795Z","signature_b64":"EHJ+74mtPDQvLbPyePAsuEUgmwngaSFTc1CbmUoCz4wy/5f6VV6F0FhrFOZWF6ri2+GvIu7TNu9PaWdXJepCCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2fd204aa23eae05a1eb8152a78c399c6404e878645b6abb98b2f53b39a067fc2","last_reissued_at":"2026-07-05T11:35:55.533256Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:35:55.533256Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.21018","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":"2026-07-05T11:35:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fCGNlOgVG4mG8M22P+ZHQWeiCkw18aE1MGRsFlGRHeh2VYOO8T/u3DDkkkC6tnjbiGYzJ8GJKqcWwFaOD9yrCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T12:26:29.289586Z"},"content_sha256":"20bcea7f8a5e41d2dcee6894faf9bf959718151a968bb0412de56bbfec64e1ff","schema_version":"1.0","event_id":"sha256:20bcea7f8a5e41d2dcee6894faf9bf959718151a968bb0412de56bbfec64e1ff"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:F7JAJKRD5LQFUHVYCUVHRQ4ZYZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"HYPEROFA: Expanding LLM Vocabulary to New Languages via Hypernetwork-Based Embedding Initialization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Enes \\\"Ozeren, Hinrich Sch\\\"utze, Yihong Liu","submitted_at":"2025-04-21T19:40:32Z","abstract_excerpt":"Many pre-trained language models (PLMs) exhibit suboptimal performance on mid- and low-resource languages, largely due to limited exposure to these languages during pre-training. A common strategy to address this is to introduce new tokens specific to the target languages, initialize their embeddings, and apply continual pre-training on target-language data. Among such methods, OFA (Liu et al., 2024a) proposes a similarity-based subword embedding initialization heuristic that is both effective and efficient. However, OFA restricts target-language token embeddings to be convex combinations of a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.21018","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/2504.21018/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":"2026-07-05T11:35:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PVhx2q2827zzlAdHM0em859CB9agKI/L288Ba3uy35dupttIDlDyP/BNV3ctoxNFcCMOgGaPcn6F2hs/B9riAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T12:26:29.290390Z"},"content_sha256":"93d521fc80f3714484d08fbb5f6b19e6df665077646d00492a162456d83e5587","schema_version":"1.0","event_id":"sha256:93d521fc80f3714484d08fbb5f6b19e6df665077646d00492a162456d83e5587"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F7JAJKRD5LQFUHVYCUVHRQ4ZYZ/bundle.json","state_url":"https://pith.science/pith/F7JAJKRD5LQFUHVYCUVHRQ4ZYZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F7JAJKRD5LQFUHVYCUVHRQ4ZYZ/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":"2026-08-18T12:26:29Z","links":{"resolver":"https://pith.science/pith/F7JAJKRD5LQFUHVYCUVHRQ4ZYZ","bundle":"https://pith.science/pith/F7JAJKRD5LQFUHVYCUVHRQ4ZYZ/bundle.json","state":"https://pith.science/pith/F7JAJKRD5LQFUHVYCUVHRQ4ZYZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F7JAJKRD5LQFUHVYCUVHRQ4ZYZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:F7JAJKRD5LQFUHVYCUVHRQ4ZYZ","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":"f207d99e0e33d742389758daa5467c91b12c914a47efa337832b2fcfbf1528f6","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-21T19:40:32Z","title_canon_sha256":"d708f05e8a83a29ec5f5ffaa182a1a0b81afa3c24503cb9912ac26b9dbd59fb8"},"schema_version":"1.0","source":{"id":"2504.21018","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.21018","created_at":"2026-07-05T11:35:55Z"},{"alias_kind":"arxiv_version","alias_value":"2504.21018v2","created_at":"2026-07-05T11:35:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.21018","created_at":"2026-07-05T11:35:55Z"},{"alias_kind":"pith_short_12","alias_value":"F7JAJKRD5LQF","created_at":"2026-07-05T11:35:55Z"},{"alias_kind":"pith_short_16","alias_value":"F7JAJKRD5LQFUHVY","created_at":"2026-07-05T11:35:55Z"},{"alias_kind":"pith_short_8","alias_value":"F7JAJKRD","created_at":"2026-07-05T11:35:55Z"}],"graph_snapshots":[{"event_id":"sha256:93d521fc80f3714484d08fbb5f6b19e6df665077646d00492a162456d83e5587","target":"graph","created_at":"2026-07-05T11:35:55Z","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/2504.21018/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many pre-trained language models (PLMs) exhibit suboptimal performance on mid- and low-resource languages, largely due to limited exposure to these languages during pre-training. A common strategy to address this is to introduce new tokens specific to the target languages, initialize their embeddings, and apply continual pre-training on target-language data. Among such methods, OFA (Liu et al., 2024a) proposes a similarity-based subword embedding initialization heuristic that is both effective and efficient. However, OFA restricts target-language token embeddings to be convex combinations of a","authors_text":"Enes \\\"Ozeren, Hinrich Sch\\\"utze, Yihong Liu","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-21T19:40:32Z","title":"HYPEROFA: Expanding LLM Vocabulary to New Languages via Hypernetwork-Based Embedding Initialization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.21018","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":"sha256:20bcea7f8a5e41d2dcee6894faf9bf959718151a968bb0412de56bbfec64e1ff","target":"record","created_at":"2026-07-05T11:35:55Z","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":"f207d99e0e33d742389758daa5467c91b12c914a47efa337832b2fcfbf1528f6","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-21T19:40:32Z","title_canon_sha256":"d708f05e8a83a29ec5f5ffaa182a1a0b81afa3c24503cb9912ac26b9dbd59fb8"},"schema_version":"1.0","source":{"id":"2504.21018","kind":"arxiv","version":2}},"canonical_sha256":"2fd204aa23eae05a1eb8152a78c399c6404e878645b6abb98b2f53b39a067fc2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2fd204aa23eae05a1eb8152a78c399c6404e878645b6abb98b2f53b39a067fc2","first_computed_at":"2026-07-05T11:35:55.533256Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:35:55.533256Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EHJ+74mtPDQvLbPyePAsuEUgmwngaSFTc1CbmUoCz4wy/5f6VV6F0FhrFOZWF6ri2+GvIu7TNu9PaWdXJepCCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:35:55.533795Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.21018","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:20bcea7f8a5e41d2dcee6894faf9bf959718151a968bb0412de56bbfec64e1ff","sha256:93d521fc80f3714484d08fbb5f6b19e6df665077646d00492a162456d83e5587"],"state_sha256":"a5586718608b3b7eb1ba4fe84872b86c36e944225221559ec845a8d4154f4cdd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nbUs4jjn1Euu1O21S9a3qKua4+3j7TflGdRgRIBTCA1MorLR56/CKvDd0bUaVmebQC0hBedxWWVuXeE8Lf3LBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T12:26:29.296065Z","bundle_sha256":"6d5f8335cf3341066c785a5ff3233d15ce05e11c67c804c204302cc7617add74"}}