{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MBWEBHK6UNDXCNC7NG67RRIVZY","short_pith_number":"pith:MBWEBHK6","schema_version":"1.0","canonical_sha256":"606c409d5ea34771345f69bdf8c515ce305e6d8d8f629aa106f0c2dbcb068f21","source":{"kind":"arxiv","id":"2406.00040","version":2},"attestation_state":"computed","paper":{"title":"Unveiling Themes in Judicial Proceedings: A Cross-Country Study Using Topic Modeling on Legal Documents from India and the UK","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amit Agarwal, Durga Toshniwal, Krish Didwania","submitted_at":"2024-05-27T16:26:50Z","abstract_excerpt":"Legal documents are indispensable in every country for legal practices and serve as the primary source of information regarding previous cases and employed statutes. In today's world, with an increasing number of judicial cases, it is crucial to systematically categorize past cases into subgroups, which can then be utilized for upcoming cases and practices. Our primary focus in this endeavor was to annotate cases using topic modeling algorithms such as Latent Dirichlet Allocation, Non-Negative Matrix Factorization, and Bertopic for a collection of lengthy legal documents from India and the UK."},"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":"2406.00040","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-27T16:26:50Z","cross_cats_sorted":[],"title_canon_sha256":"52cecddeecbd4a61f242a6d6814bbe114105ad97b205fb1ac210ce7a8faec9d0","abstract_canon_sha256":"469741dcf2ccf8d9d1c4551b294d077eec51c906677986ae9a0d54d2ae1c05ba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:00:49.288100Z","signature_b64":"PZMEKmEd5J5VPvhADY3FBqrN5+QhQfbBApel+VryiuQE4eqIAUOIkgOwZCvmlZUE9ntCa3ab/bvq0H00VNv7BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"606c409d5ea34771345f69bdf8c515ce305e6d8d8f629aa106f0c2dbcb068f21","last_reissued_at":"2026-07-05T09:00:49.287604Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:00:49.287604Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unveiling Themes in Judicial Proceedings: A Cross-Country Study Using Topic Modeling on Legal Documents from India and the UK","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amit Agarwal, Durga Toshniwal, Krish Didwania","submitted_at":"2024-05-27T16:26:50Z","abstract_excerpt":"Legal documents are indispensable in every country for legal practices and serve as the primary source of information regarding previous cases and employed statutes. In today's world, with an increasing number of judicial cases, it is crucial to systematically categorize past cases into subgroups, which can then be utilized for upcoming cases and practices. Our primary focus in this endeavor was to annotate cases using topic modeling algorithms such as Latent Dirichlet Allocation, Non-Negative Matrix Factorization, and Bertopic for a collection of lengthy legal documents from India and the UK."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.00040","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/2406.00040/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":"2406.00040","created_at":"2026-07-05T09:00:49.287662+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.00040v2","created_at":"2026-07-05T09:00:49.287662+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.00040","created_at":"2026-07-05T09:00:49.287662+00:00"},{"alias_kind":"pith_short_12","alias_value":"MBWEBHK6UNDX","created_at":"2026-07-05T09:00:49.287662+00:00"},{"alias_kind":"pith_short_16","alias_value":"MBWEBHK6UNDXCNC7","created_at":"2026-07-05T09:00:49.287662+00:00"},{"alias_kind":"pith_short_8","alias_value":"MBWEBHK6","created_at":"2026-07-05T09:00:49.287662+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.00990","citing_title":"Hybrid Topic-Semantic Labeling and Graph Embeddings for Unsupervised Legal Document Clustering","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MBWEBHK6UNDXCNC7NG67RRIVZY","json":"https://pith.science/pith/MBWEBHK6UNDXCNC7NG67RRIVZY.json","graph_json":"https://pith.science/api/pith-number/MBWEBHK6UNDXCNC7NG67RRIVZY/graph.json","events_json":"https://pith.science/api/pith-number/MBWEBHK6UNDXCNC7NG67RRIVZY/events.json","paper":"https://pith.science/paper/MBWEBHK6"},"agent_actions":{"view_html":"https://pith.science/pith/MBWEBHK6UNDXCNC7NG67RRIVZY","download_json":"https://pith.science/pith/MBWEBHK6UNDXCNC7NG67RRIVZY.json","view_paper":"https://pith.science/paper/MBWEBHK6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.00040&json=true","fetch_graph":"https://pith.science/api/pith-number/MBWEBHK6UNDXCNC7NG67RRIVZY/graph.json","fetch_events":"https://pith.science/api/pith-number/MBWEBHK6UNDXCNC7NG67RRIVZY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MBWEBHK6UNDXCNC7NG67RRIVZY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MBWEBHK6UNDXCNC7NG67RRIVZY/action/storage_attestation","attest_author":"https://pith.science/pith/MBWEBHK6UNDXCNC7NG67RRIVZY/action/author_attestation","sign_citation":"https://pith.science/pith/MBWEBHK6UNDXCNC7NG67RRIVZY/action/citation_signature","submit_replication":"https://pith.science/pith/MBWEBHK6UNDXCNC7NG67RRIVZY/action/replication_record"}},"created_at":"2026-07-05T09:00:49.287662+00:00","updated_at":"2026-07-05T09:00:49.287662+00:00"}