{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OCUVPBVGFSEOH3OY63UHV4DBSE","short_pith_number":"pith:OCUVPBVG","schema_version":"1.0","canonical_sha256":"70a95786a62c88e3edd8f6e87af06191288eb3fecd0d8d9b34f82c69dd7e89b3","source":{"kind":"arxiv","id":"2509.00990","version":1},"attestation_state":"computed","paper":{"title":"Hybrid Topic-Semantic Labeling and Graph Embeddings for Unsupervised Legal Document Clustering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"stat.ML","authors_text":"Deepak Bastola, Woohyeok Choi","submitted_at":"2025-08-31T20:53:59Z","abstract_excerpt":"Legal documents pose unique challenges for text classification due to their domain-specific language and often limited labeled data. This paper proposes a hybrid approach for classifying legal texts by combining unsupervised topic and graph embeddings with a supervised model. We employ Top2Vec to learn semantic document embeddings and automatically discover latent topics, and Node2Vec to capture structural relationships via a bipartite graph of legal documents. The embeddings are combined and clustered using KMeans, yielding coherent groupings of documents. Our computations on a legal document"},"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":"2509.00990","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-08-31T20:53:59Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"e4cc01506c4c5f468e151c0cf9f617ea84a3aeb07ffb4ecb92b741b0ff0f847a","abstract_canon_sha256":"78e58ddb199cf3c89381bf6213b692879685231e55a7a9406ee445a0bca6574d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:02:51.907416Z","signature_b64":"wO5PiTUVilxBSf3uRHHJKCp9wfKigKO2o0EAsLzUGqLHSPeo9H3a/g/U5YmHonemMUhm+YvYmXNL5QxaD/fZCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70a95786a62c88e3edd8f6e87af06191288eb3fecd0d8d9b34f82c69dd7e89b3","last_reissued_at":"2026-07-05T12:02:51.906808Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:02:51.906808Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hybrid Topic-Semantic Labeling and Graph Embeddings for Unsupervised Legal Document Clustering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"stat.ML","authors_text":"Deepak Bastola, Woohyeok Choi","submitted_at":"2025-08-31T20:53:59Z","abstract_excerpt":"Legal documents pose unique challenges for text classification due to their domain-specific language and often limited labeled data. This paper proposes a hybrid approach for classifying legal texts by combining unsupervised topic and graph embeddings with a supervised model. We employ Top2Vec to learn semantic document embeddings and automatically discover latent topics, and Node2Vec to capture structural relationships via a bipartite graph of legal documents. The embeddings are combined and clustered using KMeans, yielding coherent groupings of documents. Our computations on a legal document"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.00990","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/2509.00990/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":"2509.00990","created_at":"2026-07-05T12:02:51.906871+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.00990v1","created_at":"2026-07-05T12:02:51.906871+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.00990","created_at":"2026-07-05T12:02:51.906871+00:00"},{"alias_kind":"pith_short_12","alias_value":"OCUVPBVGFSEO","created_at":"2026-07-05T12:02:51.906871+00:00"},{"alias_kind":"pith_short_16","alias_value":"OCUVPBVGFSEOH3OY","created_at":"2026-07-05T12:02:51.906871+00:00"},{"alias_kind":"pith_short_8","alias_value":"OCUVPBVG","created_at":"2026-07-05T12:02:51.906871+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/OCUVPBVGFSEOH3OY63UHV4DBSE","json":"https://pith.science/pith/OCUVPBVGFSEOH3OY63UHV4DBSE.json","graph_json":"https://pith.science/api/pith-number/OCUVPBVGFSEOH3OY63UHV4DBSE/graph.json","events_json":"https://pith.science/api/pith-number/OCUVPBVGFSEOH3OY63UHV4DBSE/events.json","paper":"https://pith.science/paper/OCUVPBVG"},"agent_actions":{"view_html":"https://pith.science/pith/OCUVPBVGFSEOH3OY63UHV4DBSE","download_json":"https://pith.science/pith/OCUVPBVGFSEOH3OY63UHV4DBSE.json","view_paper":"https://pith.science/paper/OCUVPBVG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.00990&json=true","fetch_graph":"https://pith.science/api/pith-number/OCUVPBVGFSEOH3OY63UHV4DBSE/graph.json","fetch_events":"https://pith.science/api/pith-number/OCUVPBVGFSEOH3OY63UHV4DBSE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OCUVPBVGFSEOH3OY63UHV4DBSE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OCUVPBVGFSEOH3OY63UHV4DBSE/action/storage_attestation","attest_author":"https://pith.science/pith/OCUVPBVGFSEOH3OY63UHV4DBSE/action/author_attestation","sign_citation":"https://pith.science/pith/OCUVPBVGFSEOH3OY63UHV4DBSE/action/citation_signature","submit_replication":"https://pith.science/pith/OCUVPBVGFSEOH3OY63UHV4DBSE/action/replication_record"}},"created_at":"2026-07-05T12:02:51.906871+00:00","updated_at":"2026-07-05T12:02:51.906871+00:00"}