{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:OMBDO3T622J7PVXL4VS7MYJJW5","short_pith_number":"pith:OMBDO3T6","canonical_record":{"source":{"id":"2406.15032","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-21T10:25:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4763d49640e5c80121d6e1e7cf0342b92e48948a03e9e44e2d3c233be9380534","abstract_canon_sha256":"26dcdc539b553a4412afc50874354c588b787343582def7b5696b0c361453e43"},"schema_version":"1.0"},"canonical_sha256":"7302376e7ed693f7d6ebe565f66129b74416921fcb6746ea88cc7a42efd50682","source":{"kind":"arxiv","id":"2406.15032","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.15032","created_at":"2026-07-05T08:35:12Z"},{"alias_kind":"arxiv_version","alias_value":"2406.15032v1","created_at":"2026-07-05T08:35:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.15032","created_at":"2026-07-05T08:35:12Z"},{"alias_kind":"pith_short_12","alias_value":"OMBDO3T622J7","created_at":"2026-07-05T08:35:12Z"},{"alias_kind":"pith_short_16","alias_value":"OMBDO3T622J7PVXL","created_at":"2026-07-05T08:35:12Z"},{"alias_kind":"pith_short_8","alias_value":"OMBDO3T6","created_at":"2026-07-05T08:35:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:OMBDO3T622J7PVXL4VS7MYJJW5","target":"record","payload":{"canonical_record":{"source":{"id":"2406.15032","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-21T10:25:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4763d49640e5c80121d6e1e7cf0342b92e48948a03e9e44e2d3c233be9380534","abstract_canon_sha256":"26dcdc539b553a4412afc50874354c588b787343582def7b5696b0c361453e43"},"schema_version":"1.0"},"canonical_sha256":"7302376e7ed693f7d6ebe565f66129b74416921fcb6746ea88cc7a42efd50682","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:35:12.486055Z","signature_b64":"79CmURVaMLUpJE2V3Qxs31zMykAwcM5tjVwUYqq1MV+nI6ZJc5WgnJrQCi9z3GXEZ9uM1zqgYS4Aoyx/KXyFDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7302376e7ed693f7d6ebe565f66129b74416921fcb6746ea88cc7a42efd50682","last_reissued_at":"2026-07-05T08:35:12.485629Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:35:12.485629Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.15032","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":"2026-07-05T08:35:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7jFFH4T2Olf7JEbiF2V0JrdLJjwKUHyv3MW11KuIk0FNwz/kn8JE3nqxjzr1Lmk9JcnHLxbpOYR5x+Zk957DBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T19:19:39.336912Z"},"content_sha256":"292c62f031322021c93d9150f055a592dfad88c7ae9c68c0b13dafddd24269a1","schema_version":"1.0","event_id":"sha256:292c62f031322021c93d9150f055a592dfad88c7ae9c68c0b13dafddd24269a1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:OMBDO3T622J7PVXL4VS7MYJJW5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GiusBERTo: A Legal Language Model for Personal Data De-identification in Italian Court of Auditors Decisions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Carla Morrone, Daniela Battisti, Dario Pettazzoni, Giulio Salierno, Luca Attias, Rosamaria Bert\\`e","submitted_at":"2024-06-21T10:25:26Z","abstract_excerpt":"Recent advances in Natural Language Processing have demonstrated the effectiveness of pretrained language models like BERT for a variety of downstream tasks. We present GiusBERTo, the first BERT-based model specialized for anonymizing personal data in Italian legal documents. GiusBERTo is trained on a large dataset of Court of Auditors decisions to recognize entities to anonymize, including names, dates, locations, while retaining contextual relevance. We evaluate GiusBERTo on a held-out test set and achieve 97% token-level accuracy. GiusBERTo provides the Italian legal community with an accur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.15032","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/2406.15032/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":"2026-07-05T08:35:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jh0x+GpUWkx502u/ioqH1AuShZHYrsVUkYbqrE3oqwWviinVLQUjb1vMAneFANe2LpscR+UvX937bJHZ+07CAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T19:19:39.337473Z"},"content_sha256":"658658a372974032692d3bf49c84c10b05c7af0332540362154f1d128c12f7ab","schema_version":"1.0","event_id":"sha256:658658a372974032692d3bf49c84c10b05c7af0332540362154f1d128c12f7ab"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OMBDO3T622J7PVXL4VS7MYJJW5/bundle.json","state_url":"https://pith.science/pith/OMBDO3T622J7PVXL4VS7MYJJW5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OMBDO3T622J7PVXL4VS7MYJJW5/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":"2026-08-16T19:19:39Z","links":{"resolver":"https://pith.science/pith/OMBDO3T622J7PVXL4VS7MYJJW5","bundle":"https://pith.science/pith/OMBDO3T622J7PVXL4VS7MYJJW5/bundle.json","state":"https://pith.science/pith/OMBDO3T622J7PVXL4VS7MYJJW5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OMBDO3T622J7PVXL4VS7MYJJW5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OMBDO3T622J7PVXL4VS7MYJJW5","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":"26dcdc539b553a4412afc50874354c588b787343582def7b5696b0c361453e43","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-21T10:25:26Z","title_canon_sha256":"4763d49640e5c80121d6e1e7cf0342b92e48948a03e9e44e2d3c233be9380534"},"schema_version":"1.0","source":{"id":"2406.15032","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.15032","created_at":"2026-07-05T08:35:12Z"},{"alias_kind":"arxiv_version","alias_value":"2406.15032v1","created_at":"2026-07-05T08:35:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.15032","created_at":"2026-07-05T08:35:12Z"},{"alias_kind":"pith_short_12","alias_value":"OMBDO3T622J7","created_at":"2026-07-05T08:35:12Z"},{"alias_kind":"pith_short_16","alias_value":"OMBDO3T622J7PVXL","created_at":"2026-07-05T08:35:12Z"},{"alias_kind":"pith_short_8","alias_value":"OMBDO3T6","created_at":"2026-07-05T08:35:12Z"}],"graph_snapshots":[{"event_id":"sha256:658658a372974032692d3bf49c84c10b05c7af0332540362154f1d128c12f7ab","target":"graph","created_at":"2026-07-05T08:35:12Z","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/2406.15032/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in Natural Language Processing have demonstrated the effectiveness of pretrained language models like BERT for a variety of downstream tasks. We present GiusBERTo, the first BERT-based model specialized for anonymizing personal data in Italian legal documents. GiusBERTo is trained on a large dataset of Court of Auditors decisions to recognize entities to anonymize, including names, dates, locations, while retaining contextual relevance. We evaluate GiusBERTo on a held-out test set and achieve 97% token-level accuracy. GiusBERTo provides the Italian legal community with an accur","authors_text":"Carla Morrone, Daniela Battisti, Dario Pettazzoni, Giulio Salierno, Luca Attias, Rosamaria Bert\\`e","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-21T10:25:26Z","title":"GiusBERTo: A Legal Language Model for Personal Data De-identification in Italian Court of Auditors Decisions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.15032","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":"sha256:292c62f031322021c93d9150f055a592dfad88c7ae9c68c0b13dafddd24269a1","target":"record","created_at":"2026-07-05T08:35:12Z","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":"26dcdc539b553a4412afc50874354c588b787343582def7b5696b0c361453e43","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-21T10:25:26Z","title_canon_sha256":"4763d49640e5c80121d6e1e7cf0342b92e48948a03e9e44e2d3c233be9380534"},"schema_version":"1.0","source":{"id":"2406.15032","kind":"arxiv","version":1}},"canonical_sha256":"7302376e7ed693f7d6ebe565f66129b74416921fcb6746ea88cc7a42efd50682","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7302376e7ed693f7d6ebe565f66129b74416921fcb6746ea88cc7a42efd50682","first_computed_at":"2026-07-05T08:35:12.485629Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:35:12.485629Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"79CmURVaMLUpJE2V3Qxs31zMykAwcM5tjVwUYqq1MV+nI6ZJc5WgnJrQCi9z3GXEZ9uM1zqgYS4Aoyx/KXyFDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:35:12.486055Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.15032","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:292c62f031322021c93d9150f055a592dfad88c7ae9c68c0b13dafddd24269a1","sha256:658658a372974032692d3bf49c84c10b05c7af0332540362154f1d128c12f7ab"],"state_sha256":"286e4c72b998c6bed5b0f714f75b9c6d5f0ddbe33eb65df7cbf7b127d2aacc60"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T7XGFwszjltFG5n2pl+k4DhfYgFESjWzUIAfH15XE5AiR28edLOCswj1GZyPCDeA7gKoHbLMc7/1DK4VFWpRCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T19:19:39.341705Z","bundle_sha256":"0c0cf5c187305d02454461f59e4b5aefeca872f14849b7b91016dc5527c324c1"}}