{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZTUO4OH4WZB4ZJCAQO5LHD33GD","short_pith_number":"pith:ZTUO4OH4","schema_version":"1.0","canonical_sha256":"cce8ee38fcb643cca44083bab38f7b30ea07b0b4a03fb3048fc037d46b9de50d","source":{"kind":"arxiv","id":"2305.17284","version":1},"attestation_state":"computed","paper":{"title":"GC-Flow: A Graph-Based Flow Network for Effective Clustering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Farzaneh Mirzazadeh, Jie Chen, Tianchun Wang, Xiang Zhang","submitted_at":"2023-05-26T22:11:38Z","abstract_excerpt":"Graph convolutional networks (GCNs) are \\emph{discriminative models} that directly model the class posterior $p(y|\\mathbf{x})$ for semi-supervised classification of graph data. While being effective, as a representation learning approach, the node representations extracted from a GCN often miss useful information for effective clustering, because the objectives are different. In this work, we design normalizing flows that replace GCN layers, leading to a \\emph{generative model} that models both the class conditional likelihood $p(\\mathbf{x}|y)$ and the class prior $p(y)$. The resulting neural "},"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":"2305.17284","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-26T22:11:38Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"dd1343c42ea32ec1af3b66ff79b0ec466479baa5d306299f00a5bc331a3e8145","abstract_canon_sha256":"195954a893032ad4082cb419044d065bd36f98a2be61cebe74be1d8fb2ebb7a0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:14:26.006808Z","signature_b64":"RlGgfMTNIASVQMaKx7D57GAvqaRcF9ryOg/PxHkWkB/SbZON+wXAozrLA0hu5zkP27lqGzozL2Xq+QsK2/08Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cce8ee38fcb643cca44083bab38f7b30ea07b0b4a03fb3048fc037d46b9de50d","last_reissued_at":"2026-07-05T06:14:26.006340Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:14:26.006340Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GC-Flow: A Graph-Based Flow Network for Effective Clustering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Farzaneh Mirzazadeh, Jie Chen, Tianchun Wang, Xiang Zhang","submitted_at":"2023-05-26T22:11:38Z","abstract_excerpt":"Graph convolutional networks (GCNs) are \\emph{discriminative models} that directly model the class posterior $p(y|\\mathbf{x})$ for semi-supervised classification of graph data. While being effective, as a representation learning approach, the node representations extracted from a GCN often miss useful information for effective clustering, because the objectives are different. In this work, we design normalizing flows that replace GCN layers, leading to a \\emph{generative model} that models both the class conditional likelihood $p(\\mathbf{x}|y)$ and the class prior $p(y)$. The resulting neural "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.17284","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/2305.17284/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":"2305.17284","created_at":"2026-07-05T06:14:26.006401+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.17284v1","created_at":"2026-07-05T06:14:26.006401+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.17284","created_at":"2026-07-05T06:14:26.006401+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZTUO4OH4WZB4","created_at":"2026-07-05T06:14:26.006401+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZTUO4OH4WZB4ZJCA","created_at":"2026-07-05T06:14:26.006401+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZTUO4OH4","created_at":"2026-07-05T06:14:26.006401+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.14728","citing_title":"K-GBS3FCM -- KNN Graph-Based Safe Semi-Supervised Fuzzy C-Means","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZTUO4OH4WZB4ZJCAQO5LHD33GD","json":"https://pith.science/pith/ZTUO4OH4WZB4ZJCAQO5LHD33GD.json","graph_json":"https://pith.science/api/pith-number/ZTUO4OH4WZB4ZJCAQO5LHD33GD/graph.json","events_json":"https://pith.science/api/pith-number/ZTUO4OH4WZB4ZJCAQO5LHD33GD/events.json","paper":"https://pith.science/paper/ZTUO4OH4"},"agent_actions":{"view_html":"https://pith.science/pith/ZTUO4OH4WZB4ZJCAQO5LHD33GD","download_json":"https://pith.science/pith/ZTUO4OH4WZB4ZJCAQO5LHD33GD.json","view_paper":"https://pith.science/paper/ZTUO4OH4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.17284&json=true","fetch_graph":"https://pith.science/api/pith-number/ZTUO4OH4WZB4ZJCAQO5LHD33GD/graph.json","fetch_events":"https://pith.science/api/pith-number/ZTUO4OH4WZB4ZJCAQO5LHD33GD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZTUO4OH4WZB4ZJCAQO5LHD33GD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZTUO4OH4WZB4ZJCAQO5LHD33GD/action/storage_attestation","attest_author":"https://pith.science/pith/ZTUO4OH4WZB4ZJCAQO5LHD33GD/action/author_attestation","sign_citation":"https://pith.science/pith/ZTUO4OH4WZB4ZJCAQO5LHD33GD/action/citation_signature","submit_replication":"https://pith.science/pith/ZTUO4OH4WZB4ZJCAQO5LHD33GD/action/replication_record"}},"created_at":"2026-07-05T06:14:26.006401+00:00","updated_at":"2026-07-05T06:14:26.006401+00:00"}