{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:DL3F6W6OGO3MBLV2OO35TZECGE","short_pith_number":"pith:DL3F6W6O","schema_version":"1.0","canonical_sha256":"1af65f5bce33b6c0aeba73b7d9e4823119797eeefc9912e0df8f2891725b66a1","source":{"kind":"arxiv","id":"2004.14253","version":1},"attestation_state":"computed","paper":{"title":"GePpeTto Carves Italian into a Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Felice Dell'Orletta, Lorenzo De Mattei, Malvina Nissim, Marco Guerini, Michele Cafagna","submitted_at":"2020-04-29T15:02:01Z","abstract_excerpt":"In the last few years, pre-trained neural architectures have provided impressive improvements across several NLP tasks. Still, generative language models are available mainly for English. We develop GePpeTto, the first generative language model for Italian, built using the GPT-2 architecture. We provide a thorough analysis of GePpeTto's quality by means of both an automatic and a human-based evaluation. The automatic assessment consists in (i) calculating perplexity across different genres and (ii) a profiling analysis over GePpeTto's writing characteristics. We find that GePpeTto's production"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2004.14253","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-29T15:02:01Z","cross_cats_sorted":[],"title_canon_sha256":"cfe22e96e651802bbb8c20d40e05bfe72888f9043e7ef06008b7d7dc66273c6a","abstract_canon_sha256":"df8ab89d133eba4682cdf9f7924c46097221ff7b6359784a6bbb663c6904bcef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:59:18.784662Z","signature_b64":"b/FOVDXxrB8lQL5eMILJdMwbSJr4SyhX6KdhXXzsaryzs+8nB6sR1snZ9DL48MGH2H1JWsAicD9+blTscr8tBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1af65f5bce33b6c0aeba73b7d9e4823119797eeefc9912e0df8f2891725b66a1","last_reissued_at":"2026-07-05T00:59:18.784183Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:59:18.784183Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GePpeTto Carves Italian into a Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Felice Dell'Orletta, Lorenzo De Mattei, Malvina Nissim, Marco Guerini, Michele Cafagna","submitted_at":"2020-04-29T15:02:01Z","abstract_excerpt":"In the last few years, pre-trained neural architectures have provided impressive improvements across several NLP tasks. Still, generative language models are available mainly for English. We develop GePpeTto, the first generative language model for Italian, built using the GPT-2 architecture. We provide a thorough analysis of GePpeTto's quality by means of both an automatic and a human-based evaluation. The automatic assessment consists in (i) calculating perplexity across different genres and (ii) a profiling analysis over GePpeTto's writing characteristics. We find that GePpeTto's production"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.14253","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/2004.14253/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2004.14253","created_at":"2026-07-05T00:59:18.784242+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.14253v1","created_at":"2026-07-05T00:59:18.784242+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.14253","created_at":"2026-07-05T00:59:18.784242+00:00"},{"alias_kind":"pith_short_12","alias_value":"DL3F6W6OGO3M","created_at":"2026-07-05T00:59:18.784242+00:00"},{"alias_kind":"pith_short_16","alias_value":"DL3F6W6OGO3MBLV2","created_at":"2026-07-05T00:59:18.784242+00:00"},{"alias_kind":"pith_short_8","alias_value":"DL3F6W6O","created_at":"2026-07-05T00:59:18.784242+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20369","citing_title":"CATCH-ME if you RAG: a dataset of Contextually Annotated multi-Turn Counterspeech against Hate and Misinformation Exchanges","ref_index":259,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22435","citing_title":"Assisted Counterspeech Writing at the Crossroads of Hate Speech and Misinformation","ref_index":249,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DL3F6W6OGO3MBLV2OO35TZECGE","json":"https://pith.science/pith/DL3F6W6OGO3MBLV2OO35TZECGE.json","graph_json":"https://pith.science/api/pith-number/DL3F6W6OGO3MBLV2OO35TZECGE/graph.json","events_json":"https://pith.science/api/pith-number/DL3F6W6OGO3MBLV2OO35TZECGE/events.json","paper":"https://pith.science/paper/DL3F6W6O"},"agent_actions":{"view_html":"https://pith.science/pith/DL3F6W6OGO3MBLV2OO35TZECGE","download_json":"https://pith.science/pith/DL3F6W6OGO3MBLV2OO35TZECGE.json","view_paper":"https://pith.science/paper/DL3F6W6O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.14253&json=true","fetch_graph":"https://pith.science/api/pith-number/DL3F6W6OGO3MBLV2OO35TZECGE/graph.json","fetch_events":"https://pith.science/api/pith-number/DL3F6W6OGO3MBLV2OO35TZECGE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DL3F6W6OGO3MBLV2OO35TZECGE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DL3F6W6OGO3MBLV2OO35TZECGE/action/storage_attestation","attest_author":"https://pith.science/pith/DL3F6W6OGO3MBLV2OO35TZECGE/action/author_attestation","sign_citation":"https://pith.science/pith/DL3F6W6OGO3MBLV2OO35TZECGE/action/citation_signature","submit_replication":"https://pith.science/pith/DL3F6W6OGO3MBLV2OO35TZECGE/action/replication_record"}},"created_at":"2026-07-05T00:59:18.784242+00:00","updated_at":"2026-07-05T00:59:18.784242+00:00"}