{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:FPB3LXXFFGGEDQGXO554RAU7BJ","short_pith_number":"pith:FPB3LXXF","canonical_record":{"source":{"id":"2402.09977","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-15T14:37:07Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"9fc947e57ff7da71159e7cb5534c864525a348fc6b76962d5330a5661fe13388","abstract_canon_sha256":"4cfd1934cdb9319605d0abd58cc08cb2533e2233d2ad2b247f03154376725012"},"schema_version":"1.0"},"canonical_sha256":"2bc3b5dee5298c41c0d7777bc8829f0a5eac85352ec1c0a865bda7474dface98","source":{"kind":"arxiv","id":"2402.09977","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.09977","created_at":"2026-07-05T07:45:39Z"},{"alias_kind":"arxiv_version","alias_value":"2402.09977v1","created_at":"2026-07-05T07:45:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.09977","created_at":"2026-07-05T07:45:39Z"},{"alias_kind":"pith_short_12","alias_value":"FPB3LXXFFGGE","created_at":"2026-07-05T07:45:39Z"},{"alias_kind":"pith_short_16","alias_value":"FPB3LXXFFGGEDQGX","created_at":"2026-07-05T07:45:39Z"},{"alias_kind":"pith_short_8","alias_value":"FPB3LXXF","created_at":"2026-07-05T07:45:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:FPB3LXXFFGGEDQGXO554RAU7BJ","target":"record","payload":{"canonical_record":{"source":{"id":"2402.09977","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-15T14:37:07Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"9fc947e57ff7da71159e7cb5534c864525a348fc6b76962d5330a5661fe13388","abstract_canon_sha256":"4cfd1934cdb9319605d0abd58cc08cb2533e2233d2ad2b247f03154376725012"},"schema_version":"1.0"},"canonical_sha256":"2bc3b5dee5298c41c0d7777bc8829f0a5eac85352ec1c0a865bda7474dface98","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:45:39.693683Z","signature_b64":"CARRHRhgpKPMpMteXBQez1baVETOPMnYbPT9wkbAfnrqNhD/9PdFDUOEED+yInhuH+GtUjIEmiL0IXYHdABVCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2bc3b5dee5298c41c0d7777bc8829f0a5eac85352ec1c0a865bda7474dface98","last_reissued_at":"2026-07-05T07:45:39.693258Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:45:39.693258Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.09977","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":"2026-07-05T07:45:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R33N2Wvdi+juAkQVAH770z+Z8wULLDwM/J4wNYaH2xIlFdiI9+xbiOo+0E+/2s/gi7bBGJeqJzOFs6t5SEiACA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T08:34:05.289378Z"},"content_sha256":"0cf9f051c72b61d2ea2aa105928f5c2517a6ccf0bd1c6b93f23618e3f73820e0","schema_version":"1.0","event_id":"sha256:0cf9f051c72b61d2ea2aa105928f5c2517a6ccf0bd1c6b93f23618e3f73820e0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:FPB3LXXFFGGEDQGXO554RAU7BJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fast Vocabulary Transfer for Language Model Compression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Andrea Zugarini, Leonardo Rigutini, Leonidas Gee, Paolo Torroni","submitted_at":"2024-02-15T14:37:07Z","abstract_excerpt":"Real-world business applications require a trade-off between language model performance and size. We propose a new method for model compression that relies on vocabulary transfer. We evaluate the method on various vertical domains and downstream tasks. Our results indicate that vocabulary transfer can be effectively used in combination with other compression techniques, yielding a significant reduction in model size and inference time while marginally compromising on performance."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.09977","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/2402.09977/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":"2026-07-05T07:45:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BJ2t15S6ZrnWI0+FCyUq7vGjT3z5c8b129HEKAIxwiPU/YIZnpiE9dH6qj7pHOmoObjM4+TQOcpZcS6qLISOBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T08:34:05.289736Z"},"content_sha256":"03c84731489bcfbe628ee5957c3c28fba4d77fc09246b83007b6aa1c15cd7afb","schema_version":"1.0","event_id":"sha256:03c84731489bcfbe628ee5957c3c28fba4d77fc09246b83007b6aa1c15cd7afb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FPB3LXXFFGGEDQGXO554RAU7BJ/bundle.json","state_url":"https://pith.science/pith/FPB3LXXFFGGEDQGXO554RAU7BJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FPB3LXXFFGGEDQGXO554RAU7BJ/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":"2026-08-22T08:34:05Z","links":{"resolver":"https://pith.science/pith/FPB3LXXFFGGEDQGXO554RAU7BJ","bundle":"https://pith.science/pith/FPB3LXXFFGGEDQGXO554RAU7BJ/bundle.json","state":"https://pith.science/pith/FPB3LXXFFGGEDQGXO554RAU7BJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FPB3LXXFFGGEDQGXO554RAU7BJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FPB3LXXFFGGEDQGXO554RAU7BJ","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":"4cfd1934cdb9319605d0abd58cc08cb2533e2233d2ad2b247f03154376725012","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-15T14:37:07Z","title_canon_sha256":"9fc947e57ff7da71159e7cb5534c864525a348fc6b76962d5330a5661fe13388"},"schema_version":"1.0","source":{"id":"2402.09977","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.09977","created_at":"2026-07-05T07:45:39Z"},{"alias_kind":"arxiv_version","alias_value":"2402.09977v1","created_at":"2026-07-05T07:45:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.09977","created_at":"2026-07-05T07:45:39Z"},{"alias_kind":"pith_short_12","alias_value":"FPB3LXXFFGGE","created_at":"2026-07-05T07:45:39Z"},{"alias_kind":"pith_short_16","alias_value":"FPB3LXXFFGGEDQGX","created_at":"2026-07-05T07:45:39Z"},{"alias_kind":"pith_short_8","alias_value":"FPB3LXXF","created_at":"2026-07-05T07:45:39Z"}],"graph_snapshots":[{"event_id":"sha256:03c84731489bcfbe628ee5957c3c28fba4d77fc09246b83007b6aa1c15cd7afb","target":"graph","created_at":"2026-07-05T07:45:39Z","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/2402.09977/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Real-world business applications require a trade-off between language model performance and size. We propose a new method for model compression that relies on vocabulary transfer. We evaluate the method on various vertical domains and downstream tasks. Our results indicate that vocabulary transfer can be effectively used in combination with other compression techniques, yielding a significant reduction in model size and inference time while marginally compromising on performance.","authors_text":"Andrea Zugarini, Leonardo Rigutini, Leonidas Gee, Paolo Torroni","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-15T14:37:07Z","title":"Fast Vocabulary Transfer for Language Model Compression"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.09977","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":"sha256:0cf9f051c72b61d2ea2aa105928f5c2517a6ccf0bd1c6b93f23618e3f73820e0","target":"record","created_at":"2026-07-05T07:45:39Z","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":"4cfd1934cdb9319605d0abd58cc08cb2533e2233d2ad2b247f03154376725012","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-15T14:37:07Z","title_canon_sha256":"9fc947e57ff7da71159e7cb5534c864525a348fc6b76962d5330a5661fe13388"},"schema_version":"1.0","source":{"id":"2402.09977","kind":"arxiv","version":1}},"canonical_sha256":"2bc3b5dee5298c41c0d7777bc8829f0a5eac85352ec1c0a865bda7474dface98","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2bc3b5dee5298c41c0d7777bc8829f0a5eac85352ec1c0a865bda7474dface98","first_computed_at":"2026-07-05T07:45:39.693258Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:45:39.693258Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CARRHRhgpKPMpMteXBQez1baVETOPMnYbPT9wkbAfnrqNhD/9PdFDUOEED+yInhuH+GtUjIEmiL0IXYHdABVCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:45:39.693683Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.09977","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0cf9f051c72b61d2ea2aa105928f5c2517a6ccf0bd1c6b93f23618e3f73820e0","sha256:03c84731489bcfbe628ee5957c3c28fba4d77fc09246b83007b6aa1c15cd7afb"],"state_sha256":"0edab01f3aebb51ca397c1b2967c8c8aa81d8164b65cd69ccc9e7f04d7fded33"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VOh5aWtsmNN9YZijF8LuCi4SV00TGqoDahK+pm0qKTTtzF7QvNQJ4ebcb5T90loYyHzSKWRuulaUFuMl0bzDBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T08:34:05.292995Z","bundle_sha256":"653b645d8cacffddf3fbe72c3ebedaa1da3b8cdaaf3c5fb7a19fb84faaeb0589"}}