{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:OCUVPBVGFSEOH3OY63UHV4DBSE","short_pith_number":"pith:OCUVPBVG","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"},"canonical_sha256":"70a95786a62c88e3edd8f6e87af06191288eb3fecd0d8d9b34f82c69dd7e89b3","source":{"kind":"arxiv","id":"2509.00990","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.00990","created_at":"2026-07-05T12:02:51Z"},{"alias_kind":"arxiv_version","alias_value":"2509.00990v1","created_at":"2026-07-05T12:02:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.00990","created_at":"2026-07-05T12:02:51Z"},{"alias_kind":"pith_short_12","alias_value":"OCUVPBVGFSEO","created_at":"2026-07-05T12:02:51Z"},{"alias_kind":"pith_short_16","alias_value":"OCUVPBVGFSEOH3OY","created_at":"2026-07-05T12:02:51Z"},{"alias_kind":"pith_short_8","alias_value":"OCUVPBVG","created_at":"2026-07-05T12:02:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:OCUVPBVGFSEOH3OY63UHV4DBSE","target":"record","payload":{"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"},"canonical_sha256":"70a95786a62c88e3edd8f6e87af06191288eb3fecd0d8d9b34f82c69dd7e89b3","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"},"source_kind":"arxiv","source_id":"2509.00990","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":"2026-07-05T12:02:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iRAx7df5dFXpgfF3pHqA0TsFC67/IxiDMIpeB/rfOm3dTh1Rq7hVrK3bLal/h2qBG2RboVuJ+WLXhAVQnmBeBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T03:27:44.267308Z"},"content_sha256":"87d43470617452ef1616a041b098ca4d14e5afe36aa944a4c42498159245ff44","schema_version":"1.0","event_id":"sha256:87d43470617452ef1616a041b098ca4d14e5afe36aa944a4c42498159245ff44"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:OCUVPBVGFSEOH3OY63UHV4DBSE","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:02:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WRlJR5YYwl45Z1XnLmjr9nrulZafqBz65NjNY3tUsGA1l9evLOIYY/5h60EHxoRAvjFVXxGaPiG5qkKUQzZrCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T03:27:44.267798Z"},"content_sha256":"b94fa955bf0996465507c88f7bcb2fd69d2fefc94bfd21f71e4ca001e29857d7","schema_version":"1.0","event_id":"sha256:b94fa955bf0996465507c88f7bcb2fd69d2fefc94bfd21f71e4ca001e29857d7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OCUVPBVGFSEOH3OY63UHV4DBSE/bundle.json","state_url":"https://pith.science/pith/OCUVPBVGFSEOH3OY63UHV4DBSE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OCUVPBVGFSEOH3OY63UHV4DBSE/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":"2026-08-06T03:27:44Z","links":{"resolver":"https://pith.science/pith/OCUVPBVGFSEOH3OY63UHV4DBSE","bundle":"https://pith.science/pith/OCUVPBVGFSEOH3OY63UHV4DBSE/bundle.json","state":"https://pith.science/pith/OCUVPBVGFSEOH3OY63UHV4DBSE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OCUVPBVGFSEOH3OY63UHV4DBSE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OCUVPBVGFSEOH3OY63UHV4DBSE","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":"78e58ddb199cf3c89381bf6213b692879685231e55a7a9406ee445a0bca6574d","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-08-31T20:53:59Z","title_canon_sha256":"e4cc01506c4c5f468e151c0cf9f617ea84a3aeb07ffb4ecb92b741b0ff0f847a"},"schema_version":"1.0","source":{"id":"2509.00990","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.00990","created_at":"2026-07-05T12:02:51Z"},{"alias_kind":"arxiv_version","alias_value":"2509.00990v1","created_at":"2026-07-05T12:02:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.00990","created_at":"2026-07-05T12:02:51Z"},{"alias_kind":"pith_short_12","alias_value":"OCUVPBVGFSEO","created_at":"2026-07-05T12:02:51Z"},{"alias_kind":"pith_short_16","alias_value":"OCUVPBVGFSEOH3OY","created_at":"2026-07-05T12:02:51Z"},{"alias_kind":"pith_short_8","alias_value":"OCUVPBVG","created_at":"2026-07-05T12:02:51Z"}],"graph_snapshots":[{"event_id":"sha256:b94fa955bf0996465507c88f7bcb2fd69d2fefc94bfd21f71e4ca001e29857d7","target":"graph","created_at":"2026-07-05T12:02:51Z","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/2509.00990/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Deepak Bastola, Woohyeok Choi","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-08-31T20:53:59Z","title":"Hybrid Topic-Semantic Labeling and Graph Embeddings for Unsupervised Legal Document Clustering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.00990","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":"sha256:87d43470617452ef1616a041b098ca4d14e5afe36aa944a4c42498159245ff44","target":"record","created_at":"2026-07-05T12:02:51Z","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":"78e58ddb199cf3c89381bf6213b692879685231e55a7a9406ee445a0bca6574d","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-08-31T20:53:59Z","title_canon_sha256":"e4cc01506c4c5f468e151c0cf9f617ea84a3aeb07ffb4ecb92b741b0ff0f847a"},"schema_version":"1.0","source":{"id":"2509.00990","kind":"arxiv","version":1}},"canonical_sha256":"70a95786a62c88e3edd8f6e87af06191288eb3fecd0d8d9b34f82c69dd7e89b3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"70a95786a62c88e3edd8f6e87af06191288eb3fecd0d8d9b34f82c69dd7e89b3","first_computed_at":"2026-07-05T12:02:51.906808Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:02:51.906808Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wO5PiTUVilxBSf3uRHHJKCp9wfKigKO2o0EAsLzUGqLHSPeo9H3a/g/U5YmHonemMUhm+YvYmXNL5QxaD/fZCA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:02:51.907416Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.00990","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:87d43470617452ef1616a041b098ca4d14e5afe36aa944a4c42498159245ff44","sha256:b94fa955bf0996465507c88f7bcb2fd69d2fefc94bfd21f71e4ca001e29857d7"],"state_sha256":"55fd3f0ca1fb76cd386e9ebc6583b54605c6ea101c6ecab3601495087edaa013"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cqUYjTFSA9dK7iBU8f31GbrGuadIjhJJARHCuPhYeF6N2hErUXAzdNzgfFT5r/4tdupd2QR5soQf+nGh/gbxCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T03:27:44.271303Z","bundle_sha256":"cc4752af381c7d04b4ee856d1ad7e2e21be8d60c959ab32a52cb37fb94852fb7"}}