{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:UCLISZQU4BF6OKMLENR3KXANJO","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":"d8aa5b0beeed6d3ec84ca15ea5ab9acaf211a61fe7fb922fbccfd3bb3f34dcf4","cross_cats_sorted":["cs.IR","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-31T16:21:51Z","title_canon_sha256":"61ec394d406d254161320e779aae82a47952a41ee80d05ced6422ad3b6978ce1"},"schema_version":"1.0","source":{"id":"2201.13324","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.13324","created_at":"2026-07-05T03:52:51Z"},{"alias_kind":"arxiv_version","alias_value":"2201.13324v1","created_at":"2026-07-05T03:52:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.13324","created_at":"2026-07-05T03:52:51Z"},{"alias_kind":"pith_short_12","alias_value":"UCLISZQU4BF6","created_at":"2026-07-05T03:52:51Z"},{"alias_kind":"pith_short_16","alias_value":"UCLISZQU4BF6OKML","created_at":"2026-07-05T03:52:51Z"},{"alias_kind":"pith_short_8","alias_value":"UCLISZQU","created_at":"2026-07-05T03:52:51Z"}],"graph_snapshots":[{"event_id":"sha256:a41ccb1ed693555026abfa30da4cfb83dcb5ba01095bf464290b45c702a74a5a","target":"graph","created_at":"2026-07-05T03:52:51Z","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/2201.13324/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Benjamin Jarman, Christine Tseng, Deanna Needell, Joyce A. Chew, Longxiu Huang, Pengyu Li, Yaxuan Zheng","cross_cats":["cs.IR","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-31T16:21:51Z","title":"Guided Semi-Supervised Non-negative Matrix Factorization on Legal Documents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.13324","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:ea30109e7bc3bcfdb30a14e3710155af8577cb961f191af6c5fc8368638b4062","target":"record","created_at":"2026-07-05T03:52:51Z","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":"d8aa5b0beeed6d3ec84ca15ea5ab9acaf211a61fe7fb922fbccfd3bb3f34dcf4","cross_cats_sorted":["cs.IR","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-31T16:21:51Z","title_canon_sha256":"61ec394d406d254161320e779aae82a47952a41ee80d05ced6422ad3b6978ce1"},"schema_version":"1.0","source":{"id":"2201.13324","kind":"arxiv","version":1}},"canonical_sha256":"a096896614e04be7298b2363b55c0d4bae76446c330ec9ba8a80b3a8f64fb4c1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a096896614e04be7298b2363b55c0d4bae76446c330ec9ba8a80b3a8f64fb4c1","first_computed_at":"2026-07-05T03:52:51.011867Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:52:51.011867Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8xO1rjR6WpQ2GDg0a93PZ2gR80U5oROBXi63HwgrvoalCrVDNQgEqt+BdaLWjr1r1hMt32helAD1o5naioAWBg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:52:51.012277Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.13324","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ea30109e7bc3bcfdb30a14e3710155af8577cb961f191af6c5fc8368638b4062","sha256:a41ccb1ed693555026abfa30da4cfb83dcb5ba01095bf464290b45c702a74a5a"],"state_sha256":"311edabc715fd61335929ae9af03b27b92118de143706c99beb70c22897add08"}