{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MP3MIPS3WKXODZE2MWIK4F2CLI","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":"851f454bfc515b29284d1fbccfc9e92ead2c0ae41299ac27cbbc0397953fefc9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-13T11:06:24Z","title_canon_sha256":"be315661f14420d2d256472da08efecbf1818d683c37e8ce21000e1139795149"},"schema_version":"1.0","source":{"id":"2505.08439","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.08439","created_at":"2026-07-05T11:02:30Z"},{"alias_kind":"arxiv_version","alias_value":"2505.08439v1","created_at":"2026-07-05T11:02:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.08439","created_at":"2026-07-05T11:02:30Z"},{"alias_kind":"pith_short_12","alias_value":"MP3MIPS3WKXO","created_at":"2026-07-05T11:02:30Z"},{"alias_kind":"pith_short_16","alias_value":"MP3MIPS3WKXODZE2","created_at":"2026-07-05T11:02:30Z"},{"alias_kind":"pith_short_8","alias_value":"MP3MIPS3","created_at":"2026-07-05T11:02:30Z"}],"graph_snapshots":[{"event_id":"sha256:87841d36d9875229c758374722484095fea9c5e386b0b4f85c1d193532208a7f","target":"graph","created_at":"2026-07-05T11:02:30Z","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/2505.08439/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Topic modeling in Italian legal research is hindered by the lack of public datasets, limiting the analysis of legal themes in Supreme Court judgments. To address this, we developed a document processing pipeline that produces an anonymized dataset optimized for topic modeling.\n  The pipeline integrates document layout analysis (YOLOv8x), optical character recognition, and text anonymization. The DLA module achieved a mAP@50 of 0.964 and a mAP@50-95 of 0.800. The OCR detector reached a mAP@50-95 of 0.9022, and the text recognizer (TrOCR) obtained a character error rate of 0.0047 and a word erro","authors_text":"Glauco Panattoni, Marco Bertini, Matteo Marulli","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-13T11:06:24Z","title":"A document processing pipeline for the construction of a dataset for topic modeling based on the judgments of the Italian Supreme Court"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.08439","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":"sha256:36c8b49ef91a325ad48a3fa5f5debb7d67c72ffc990a9b3f1fee86578d75720b","target":"record","created_at":"2026-07-05T11:02:30Z","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":"851f454bfc515b29284d1fbccfc9e92ead2c0ae41299ac27cbbc0397953fefc9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-13T11:06:24Z","title_canon_sha256":"be315661f14420d2d256472da08efecbf1818d683c37e8ce21000e1139795149"},"schema_version":"1.0","source":{"id":"2505.08439","kind":"arxiv","version":1}},"canonical_sha256":"63f6c43e5bb2aee1e49a6590ae17425a32ef189a9e3986a2543d34af05175669","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"63f6c43e5bb2aee1e49a6590ae17425a32ef189a9e3986a2543d34af05175669","first_computed_at":"2026-07-05T11:02:30.469132Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:02:30.469132Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VU9UEe8kPbu1jBQjE2EsOyJmgQscYMigR9lk2COWjyOS3lFJU/kHBf/zTvziLknod1O3A9IqnIohjX/9SaTSDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:02:30.469556Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.08439","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:36c8b49ef91a325ad48a3fa5f5debb7d67c72ffc990a9b3f1fee86578d75720b","sha256:87841d36d9875229c758374722484095fea9c5e386b0b4f85c1d193532208a7f"],"state_sha256":"014f37cab0fe3b5b9bf2f7f8435143813a7fe3853f736bb2cc406ae648029f64"}