{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MP3MIPS3WKXODZE2MWIK4F2CLI","short_pith_number":"pith:MP3MIPS3","schema_version":"1.0","canonical_sha256":"63f6c43e5bb2aee1e49a6590ae17425a32ef189a9e3986a2543d34af05175669","source":{"kind":"arxiv","id":"2505.08439","version":1},"attestation_state":"computed","paper":{"title":"A document processing pipeline for the construction of a dataset for topic modeling based on the judgments of the Italian Supreme Court","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Glauco Panattoni, Marco Bertini, Matteo Marulli","submitted_at":"2025-05-13T11:06:24Z","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"},"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":"2505.08439","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-13T11:06:24Z","cross_cats_sorted":[],"title_canon_sha256":"be315661f14420d2d256472da08efecbf1818d683c37e8ce21000e1139795149","abstract_canon_sha256":"851f454bfc515b29284d1fbccfc9e92ead2c0ae41299ac27cbbc0397953fefc9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:02:30.469556Z","signature_b64":"VU9UEe8kPbu1jBQjE2EsOyJmgQscYMigR9lk2COWjyOS3lFJU/kHBf/zTvziLknod1O3A9IqnIohjX/9SaTSDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"63f6c43e5bb2aee1e49a6590ae17425a32ef189a9e3986a2543d34af05175669","last_reissued_at":"2026-07-05T11:02:30.469132Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:02:30.469132Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A document processing pipeline for the construction of a dataset for topic modeling based on the judgments of the Italian Supreme Court","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Glauco Panattoni, Marco Bertini, Matteo Marulli","submitted_at":"2025-05-13T11:06:24Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.08439","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/2505.08439/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":"2505.08439","created_at":"2026-07-05T11:02:30.469200+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.08439v1","created_at":"2026-07-05T11:02:30.469200+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.08439","created_at":"2026-07-05T11:02:30.469200+00:00"},{"alias_kind":"pith_short_12","alias_value":"MP3MIPS3WKXO","created_at":"2026-07-05T11:02:30.469200+00:00"},{"alias_kind":"pith_short_16","alias_value":"MP3MIPS3WKXODZE2","created_at":"2026-07-05T11:02:30.469200+00:00"},{"alias_kind":"pith_short_8","alias_value":"MP3MIPS3","created_at":"2026-07-05T11:02:30.469200+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/MP3MIPS3WKXODZE2MWIK4F2CLI","json":"https://pith.science/pith/MP3MIPS3WKXODZE2MWIK4F2CLI.json","graph_json":"https://pith.science/api/pith-number/MP3MIPS3WKXODZE2MWIK4F2CLI/graph.json","events_json":"https://pith.science/api/pith-number/MP3MIPS3WKXODZE2MWIK4F2CLI/events.json","paper":"https://pith.science/paper/MP3MIPS3"},"agent_actions":{"view_html":"https://pith.science/pith/MP3MIPS3WKXODZE2MWIK4F2CLI","download_json":"https://pith.science/pith/MP3MIPS3WKXODZE2MWIK4F2CLI.json","view_paper":"https://pith.science/paper/MP3MIPS3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.08439&json=true","fetch_graph":"https://pith.science/api/pith-number/MP3MIPS3WKXODZE2MWIK4F2CLI/graph.json","fetch_events":"https://pith.science/api/pith-number/MP3MIPS3WKXODZE2MWIK4F2CLI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MP3MIPS3WKXODZE2MWIK4F2CLI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MP3MIPS3WKXODZE2MWIK4F2CLI/action/storage_attestation","attest_author":"https://pith.science/pith/MP3MIPS3WKXODZE2MWIK4F2CLI/action/author_attestation","sign_citation":"https://pith.science/pith/MP3MIPS3WKXODZE2MWIK4F2CLI/action/citation_signature","submit_replication":"https://pith.science/pith/MP3MIPS3WKXODZE2MWIK4F2CLI/action/replication_record"}},"created_at":"2026-07-05T11:02:30.469200+00:00","updated_at":"2026-07-05T11:02:30.469200+00:00"}