{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:2P4NKKFRHWO5QAXZYHRVIOXATW","short_pith_number":"pith:2P4NKKFR","canonical_record":{"source":{"id":"2504.17025","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-23T18:12:27Z","cross_cats_sorted":[],"title_canon_sha256":"ad20e0efff760c7fb5c08caf5695aaacc399ed27a9f64b566f8260ee15dd60e8","abstract_canon_sha256":"a97c6909c87fa8c958cb6aae06eee7d02f1af30d6d057c10a050c0437bd6de10"},"schema_version":"1.0"},"canonical_sha256":"d3f8d528b13d9dd802f9c1e3543ae09dac10dadb44fc3ee21fca52d9330b8054","source":{"kind":"arxiv","id":"2504.17025","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.17025","created_at":"2026-07-05T10:53:20Z"},{"alias_kind":"arxiv_version","alias_value":"2504.17025v1","created_at":"2026-07-05T10:53:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.17025","created_at":"2026-07-05T10:53:20Z"},{"alias_kind":"pith_short_12","alias_value":"2P4NKKFRHWO5","created_at":"2026-07-05T10:53:20Z"},{"alias_kind":"pith_short_16","alias_value":"2P4NKKFRHWO5QAXZ","created_at":"2026-07-05T10:53:20Z"},{"alias_kind":"pith_short_8","alias_value":"2P4NKKFR","created_at":"2026-07-05T10:53:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:2P4NKKFRHWO5QAXZYHRVIOXATW","target":"record","payload":{"canonical_record":{"source":{"id":"2504.17025","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-23T18:12:27Z","cross_cats_sorted":[],"title_canon_sha256":"ad20e0efff760c7fb5c08caf5695aaacc399ed27a9f64b566f8260ee15dd60e8","abstract_canon_sha256":"a97c6909c87fa8c958cb6aae06eee7d02f1af30d6d057c10a050c0437bd6de10"},"schema_version":"1.0"},"canonical_sha256":"d3f8d528b13d9dd802f9c1e3543ae09dac10dadb44fc3ee21fca52d9330b8054","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:53:20.771101Z","signature_b64":"pooU9pWde6Sc/PjJeuNTPSDVfZ5uRwMaJauKG66yoOfYVGdy9LQJSoFiSEEtIRs4OF+8+7RmlQsnKELePAVcAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d3f8d528b13d9dd802f9c1e3543ae09dac10dadb44fc3ee21fca52d9330b8054","last_reissued_at":"2026-07-05T10:53:20.770600Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:53:20.770600Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.17025","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":"2026-07-05T10:53:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hccKwvwrZCTCiK5VXK77li423jbPJUNHzfQ7kk7TJTT7THIGdj0FBYXfgAVj9akcXnCqU+VRV0sraq7BJtHNCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T06:19:48.369003Z"},"content_sha256":"0e6ba7006dee44c9b1bf8b8252b58613880157f2e738cb660e923ed386e16086","schema_version":"1.0","event_id":"sha256:0e6ba7006dee44c9b1bf8b8252b58613880157f2e738cb660e923ed386e16086"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:2P4NKKFRHWO5QAXZYHRVIOXATW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Optimizing LLMs for Italian: Reducing Token Fertility and Enhancing Efficiency Through Vocabulary Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alessio Miaschi, Andrea Esuli, Andrei Stefan Bejgu, Edoardo Barba, Felice Dell'Orletta, Giovanni Puccetti, Luca Moroni, Pere-Lluis Huguet Cabot, Roberto Navigli","submitted_at":"2025-04-23T18:12:27Z","abstract_excerpt":"The number of pretrained Large Language Models (LLMs) is increasing steadily, though the majority are designed predominantly for the English language. While state-of-the-art LLMs can handle other languages, due to language contamination or some degree of multilingual pretraining data, they are not optimized for non-English languages, leading to inefficient encoding (high token \"fertility\") and slower inference speed. In this work, we thoroughly compare a variety of vocabulary adaptation techniques for optimizing English LLMs for the Italian language, and put forward Semantic Alignment Vocabula"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.17025","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/2504.17025/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":"2026-07-05T10:53:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vAln/8aE0MEweYyP1Z93Q+QptqKsxBtelHfiQlzBzkVf1NjrI8e8LGzQ2U57UCPpXkudFSQBRLFQe8DWoI3vDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T06:19:48.369388Z"},"content_sha256":"b58f37ce8e6da40823c1a0ce60b038f5ea92231f04ecd30eb566a799eff5f4a8","schema_version":"1.0","event_id":"sha256:b58f37ce8e6da40823c1a0ce60b038f5ea92231f04ecd30eb566a799eff5f4a8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2P4NKKFRHWO5QAXZYHRVIOXATW/bundle.json","state_url":"https://pith.science/pith/2P4NKKFRHWO5QAXZYHRVIOXATW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2P4NKKFRHWO5QAXZYHRVIOXATW/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":"2026-07-07T06:19:48Z","links":{"resolver":"https://pith.science/pith/2P4NKKFRHWO5QAXZYHRVIOXATW","bundle":"https://pith.science/pith/2P4NKKFRHWO5QAXZYHRVIOXATW/bundle.json","state":"https://pith.science/pith/2P4NKKFRHWO5QAXZYHRVIOXATW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2P4NKKFRHWO5QAXZYHRVIOXATW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2P4NKKFRHWO5QAXZYHRVIOXATW","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":"a97c6909c87fa8c958cb6aae06eee7d02f1af30d6d057c10a050c0437bd6de10","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-23T18:12:27Z","title_canon_sha256":"ad20e0efff760c7fb5c08caf5695aaacc399ed27a9f64b566f8260ee15dd60e8"},"schema_version":"1.0","source":{"id":"2504.17025","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.17025","created_at":"2026-07-05T10:53:20Z"},{"alias_kind":"arxiv_version","alias_value":"2504.17025v1","created_at":"2026-07-05T10:53:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.17025","created_at":"2026-07-05T10:53:20Z"},{"alias_kind":"pith_short_12","alias_value":"2P4NKKFRHWO5","created_at":"2026-07-05T10:53:20Z"},{"alias_kind":"pith_short_16","alias_value":"2P4NKKFRHWO5QAXZ","created_at":"2026-07-05T10:53:20Z"},{"alias_kind":"pith_short_8","alias_value":"2P4NKKFR","created_at":"2026-07-05T10:53:20Z"}],"graph_snapshots":[{"event_id":"sha256:b58f37ce8e6da40823c1a0ce60b038f5ea92231f04ecd30eb566a799eff5f4a8","target":"graph","created_at":"2026-07-05T10:53:20Z","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/2504.17025/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The number of pretrained Large Language Models (LLMs) is increasing steadily, though the majority are designed predominantly for the English language. While state-of-the-art LLMs can handle other languages, due to language contamination or some degree of multilingual pretraining data, they are not optimized for non-English languages, leading to inefficient encoding (high token \"fertility\") and slower inference speed. In this work, we thoroughly compare a variety of vocabulary adaptation techniques for optimizing English LLMs for the Italian language, and put forward Semantic Alignment Vocabula","authors_text":"Alessio Miaschi, Andrea Esuli, Andrei Stefan Bejgu, Edoardo Barba, Felice Dell'Orletta, Giovanni Puccetti, Luca Moroni, Pere-Lluis Huguet Cabot, Roberto Navigli","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-23T18:12:27Z","title":"Optimizing LLMs for Italian: Reducing Token Fertility and Enhancing Efficiency Through Vocabulary Adaptation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.17025","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":"sha256:0e6ba7006dee44c9b1bf8b8252b58613880157f2e738cb660e923ed386e16086","target":"record","created_at":"2026-07-05T10:53:20Z","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":"a97c6909c87fa8c958cb6aae06eee7d02f1af30d6d057c10a050c0437bd6de10","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-23T18:12:27Z","title_canon_sha256":"ad20e0efff760c7fb5c08caf5695aaacc399ed27a9f64b566f8260ee15dd60e8"},"schema_version":"1.0","source":{"id":"2504.17025","kind":"arxiv","version":1}},"canonical_sha256":"d3f8d528b13d9dd802f9c1e3543ae09dac10dadb44fc3ee21fca52d9330b8054","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d3f8d528b13d9dd802f9c1e3543ae09dac10dadb44fc3ee21fca52d9330b8054","first_computed_at":"2026-07-05T10:53:20.770600Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:53:20.770600Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pooU9pWde6Sc/PjJeuNTPSDVfZ5uRwMaJauKG66yoOfYVGdy9LQJSoFiSEEtIRs4OF+8+7RmlQsnKELePAVcAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:53:20.771101Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.17025","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0e6ba7006dee44c9b1bf8b8252b58613880157f2e738cb660e923ed386e16086","sha256:b58f37ce8e6da40823c1a0ce60b038f5ea92231f04ecd30eb566a799eff5f4a8"],"state_sha256":"df6f4eff9001fe4c7e313a38417dfafc6a6d60e480d110fc21e976ee35949523"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K8CfQLFpOtO/4orQnrt6xz+epUCtCnB5t9T9cBh1Z8tmjbiYcw+KrCSHn6bMxEFyx2J8BCVkPsa+HTd+Scv8AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T06:19:48.371383Z","bundle_sha256":"6dc931667e12e6f758694bb8076811b17cd9102fc75df5912930a51e8b8cf7b1"}}