{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IYTYEAFYFCSJC56PMJ2LB4PO73","short_pith_number":"pith:IYTYEAFY","schema_version":"1.0","canonical_sha256":"46278200b828a49177cf6274b0f1eefee4cc08b96b9af2502403c30714f2ec45","source":{"kind":"arxiv","id":"2406.12128","version":2},"attestation_state":"computed","paper":{"title":"AI \"News\" Content Farms Are Easy to Make and Hard to Detect: A Case Study in Italian","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andrea Esuli, Anna Rogers, Chiara Alzetta, Felice Dell'Orletta, Giovanni Puccetti","submitted_at":"2024-06-17T22:19:00Z","abstract_excerpt":"Large Language Models (LLMs) are increasingly used as \"content farm\" models (CFMs), to generate synthetic text that could pass for real news articles. This is already happening even for languages that do not have high-quality monolingual LLMs. We show that fine-tuning Llama (v1), mostly trained on English, on as little as 40K Italian news articles, is sufficient for producing news-like texts that native speakers of Italian struggle to identify as synthetic.\n  We investigate three LLMs and three methods of detecting synthetic texts (log-likelihood, DetectGPT, and supervised classification), fin"},"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":"2406.12128","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-17T22:19:00Z","cross_cats_sorted":[],"title_canon_sha256":"8f909f13cd554df1588926ea7f4f4025c9021c9bb400abc05461d85a3d0ee517","abstract_canon_sha256":"e07b335a02543e12ab6dde18bdc5266146836b3ef40dd124aa351b06bd355483"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:13:03.922356Z","signature_b64":"Az+9S0hRa2KUVbNZ3VGCHmo+0mqEKe8H3XYYrnWtfKVvnqWBA7m3PMnHZjayqoE0YLzYvz3oBxKiSkwaS+RXAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"46278200b828a49177cf6274b0f1eefee4cc08b96b9af2502403c30714f2ec45","last_reissued_at":"2026-07-05T09:13:03.921867Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:13:03.921867Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AI \"News\" Content Farms Are Easy to Make and Hard to Detect: A Case Study in Italian","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andrea Esuli, Anna Rogers, Chiara Alzetta, Felice Dell'Orletta, Giovanni Puccetti","submitted_at":"2024-06-17T22:19:00Z","abstract_excerpt":"Large Language Models (LLMs) are increasingly used as \"content farm\" models (CFMs), to generate synthetic text that could pass for real news articles. This is already happening even for languages that do not have high-quality monolingual LLMs. We show that fine-tuning Llama (v1), mostly trained on English, on as little as 40K Italian news articles, is sufficient for producing news-like texts that native speakers of Italian struggle to identify as synthetic.\n  We investigate three LLMs and three methods of detecting synthetic texts (log-likelihood, DetectGPT, and supervised classification), fin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.12128","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/2406.12128/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":"2406.12128","created_at":"2026-07-05T09:13:03.921922+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.12128v2","created_at":"2026-07-05T09:13:03.921922+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.12128","created_at":"2026-07-05T09:13:03.921922+00:00"},{"alias_kind":"pith_short_12","alias_value":"IYTYEAFYFCSJ","created_at":"2026-07-05T09:13:03.921922+00:00"},{"alias_kind":"pith_short_16","alias_value":"IYTYEAFYFCSJC56P","created_at":"2026-07-05T09:13:03.921922+00:00"},{"alias_kind":"pith_short_8","alias_value":"IYTYEAFY","created_at":"2026-07-05T09:13:03.921922+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IYTYEAFYFCSJC56PMJ2LB4PO73","json":"https://pith.science/pith/IYTYEAFYFCSJC56PMJ2LB4PO73.json","graph_json":"https://pith.science/api/pith-number/IYTYEAFYFCSJC56PMJ2LB4PO73/graph.json","events_json":"https://pith.science/api/pith-number/IYTYEAFYFCSJC56PMJ2LB4PO73/events.json","paper":"https://pith.science/paper/IYTYEAFY"},"agent_actions":{"view_html":"https://pith.science/pith/IYTYEAFYFCSJC56PMJ2LB4PO73","download_json":"https://pith.science/pith/IYTYEAFYFCSJC56PMJ2LB4PO73.json","view_paper":"https://pith.science/paper/IYTYEAFY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.12128&json=true","fetch_graph":"https://pith.science/api/pith-number/IYTYEAFYFCSJC56PMJ2LB4PO73/graph.json","fetch_events":"https://pith.science/api/pith-number/IYTYEAFYFCSJC56PMJ2LB4PO73/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IYTYEAFYFCSJC56PMJ2LB4PO73/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IYTYEAFYFCSJC56PMJ2LB4PO73/action/storage_attestation","attest_author":"https://pith.science/pith/IYTYEAFYFCSJC56PMJ2LB4PO73/action/author_attestation","sign_citation":"https://pith.science/pith/IYTYEAFYFCSJC56PMJ2LB4PO73/action/citation_signature","submit_replication":"https://pith.science/pith/IYTYEAFYFCSJC56PMJ2LB4PO73/action/replication_record"}},"created_at":"2026-07-05T09:13:03.921922+00:00","updated_at":"2026-07-05T09:13:03.921922+00:00"}