{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:UCLISZQU4BF6OKMLENR3KXANJO","short_pith_number":"pith:UCLISZQU","schema_version":"1.0","canonical_sha256":"a096896614e04be7298b2363b55c0d4bae76446c330ec9ba8a80b3a8f64fb4c1","source":{"kind":"arxiv","id":"2201.13324","version":1},"attestation_state":"computed","paper":{"title":"Guided Semi-Supervised Non-negative Matrix Factorization on Legal Documents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Benjamin Jarman, Christine Tseng, Deanna Needell, Joyce A. Chew, Longxiu Huang, Pengyu Li, Yaxuan Zheng","submitted_at":"2022-01-31T16:21:51Z","abstract_excerpt":"Classification and topic modeling are popular techniques in machine learning that extract information from large-scale datasets. By incorporating a priori information such as labels or important features, methods have been developed to perform classification and topic modeling tasks; however, most methods that can perform both do not allow for guidance of the topics or features. In this paper, we propose a method, namely Guided Semi-Supervised Non-negative Matrix Factorization (GSSNMF), that performs both classification and topic modeling by incorporating supervision from both pre-assigned doc"},"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":"2201.13324","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-31T16:21:51Z","cross_cats_sorted":["cs.IR","stat.ML"],"title_canon_sha256":"61ec394d406d254161320e779aae82a47952a41ee80d05ced6422ad3b6978ce1","abstract_canon_sha256":"d8aa5b0beeed6d3ec84ca15ea5ab9acaf211a61fe7fb922fbccfd3bb3f34dcf4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:52:51.012277Z","signature_b64":"8xO1rjR6WpQ2GDg0a93PZ2gR80U5oROBXi63HwgrvoalCrVDNQgEqt+BdaLWjr1r1hMt32helAD1o5naioAWBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a096896614e04be7298b2363b55c0d4bae76446c330ec9ba8a80b3a8f64fb4c1","last_reissued_at":"2026-07-05T03:52:51.011867Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:52:51.011867Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Guided Semi-Supervised Non-negative Matrix Factorization on Legal Documents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Benjamin Jarman, Christine Tseng, Deanna Needell, Joyce A. Chew, Longxiu Huang, Pengyu Li, Yaxuan Zheng","submitted_at":"2022-01-31T16:21:51Z","abstract_excerpt":"Classification and topic modeling are popular techniques in machine learning that extract information from large-scale datasets. By incorporating a priori information such as labels or important features, methods have been developed to perform classification and topic modeling tasks; however, most methods that can perform both do not allow for guidance of the topics or features. In this paper, we propose a method, namely Guided Semi-Supervised Non-negative Matrix Factorization (GSSNMF), that performs both classification and topic modeling by incorporating supervision from both pre-assigned doc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.13324","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/2201.13324/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":"2201.13324","created_at":"2026-07-05T03:52:51.011932+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.13324v1","created_at":"2026-07-05T03:52:51.011932+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.13324","created_at":"2026-07-05T03:52:51.011932+00:00"},{"alias_kind":"pith_short_12","alias_value":"UCLISZQU4BF6","created_at":"2026-07-05T03:52:51.011932+00:00"},{"alias_kind":"pith_short_16","alias_value":"UCLISZQU4BF6OKML","created_at":"2026-07-05T03:52:51.011932+00:00"},{"alias_kind":"pith_short_8","alias_value":"UCLISZQU","created_at":"2026-07-05T03:52:51.011932+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/UCLISZQU4BF6OKMLENR3KXANJO","json":"https://pith.science/pith/UCLISZQU4BF6OKMLENR3KXANJO.json","graph_json":"https://pith.science/api/pith-number/UCLISZQU4BF6OKMLENR3KXANJO/graph.json","events_json":"https://pith.science/api/pith-number/UCLISZQU4BF6OKMLENR3KXANJO/events.json","paper":"https://pith.science/paper/UCLISZQU"},"agent_actions":{"view_html":"https://pith.science/pith/UCLISZQU4BF6OKMLENR3KXANJO","download_json":"https://pith.science/pith/UCLISZQU4BF6OKMLENR3KXANJO.json","view_paper":"https://pith.science/paper/UCLISZQU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.13324&json=true","fetch_graph":"https://pith.science/api/pith-number/UCLISZQU4BF6OKMLENR3KXANJO/graph.json","fetch_events":"https://pith.science/api/pith-number/UCLISZQU4BF6OKMLENR3KXANJO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UCLISZQU4BF6OKMLENR3KXANJO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UCLISZQU4BF6OKMLENR3KXANJO/action/storage_attestation","attest_author":"https://pith.science/pith/UCLISZQU4BF6OKMLENR3KXANJO/action/author_attestation","sign_citation":"https://pith.science/pith/UCLISZQU4BF6OKMLENR3KXANJO/action/citation_signature","submit_replication":"https://pith.science/pith/UCLISZQU4BF6OKMLENR3KXANJO/action/replication_record"}},"created_at":"2026-07-05T03:52:51.011932+00:00","updated_at":"2026-07-05T03:52:51.011932+00:00"}