{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SUEZZVJBKXGTMG6QDWSRVSKV2I","short_pith_number":"pith:SUEZZVJB","schema_version":"1.0","canonical_sha256":"95099cd52155cd361bd01da51ac955d229db136467fc1959965ddfa564fac5cf","source":{"kind":"arxiv","id":"2506.11142","version":2},"attestation_state":"computed","paper":{"title":"FARCLUSS: Fuzzy Adaptive Rebalancing and Contrastive Uncertainty Learning for Semi-Supervised Semantic Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Ebenezer Tarubinga, Jenifer Kalafatovich, Seong-Whan Lee","submitted_at":"2025-06-11T03:47:08Z","abstract_excerpt":"Semi-supervised semantic segmentation (SSSS) faces persistent challenges in effectively leveraging unlabeled data, such as ineffective utilization of pseudo-labels, exacerbation of class imbalance biases, and neglect of prediction uncertainty. Current approaches often discard uncertain regions through strict thresholding favouring dominant classes. To address these limitations, we introduce a holistic framework that transforms uncertainty into a learning asset through four principal components: (1) fuzzy pseudo-labeling, which preserves soft class distributions from top-K predictions to enrich"},"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":"2506.11142","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-11T03:47:08Z","cross_cats_sorted":["cs.LG","eess.IV"],"title_canon_sha256":"ea4d3ad26cce8417db5563629fab79effc9f893e644fe36c480e53ba01dadadd","abstract_canon_sha256":"461d3fca023d1e63cb024ab9d5f51cf122c86f6d451d30fdbb33e7a82f1385ff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:25:45.895814Z","signature_b64":"JDpdwEexJkyLT3qV13DtLX2g13qog5kn+RFkgMlhx+6BRt2udbeM+n2VqV1OL8CL0wGCNilvW5AEtlmlK75FCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95099cd52155cd361bd01da51ac955d229db136467fc1959965ddfa564fac5cf","last_reissued_at":"2026-07-05T11:25:45.895325Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:25:45.895325Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FARCLUSS: Fuzzy Adaptive Rebalancing and Contrastive Uncertainty Learning for Semi-Supervised Semantic Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Ebenezer Tarubinga, Jenifer Kalafatovich, Seong-Whan Lee","submitted_at":"2025-06-11T03:47:08Z","abstract_excerpt":"Semi-supervised semantic segmentation (SSSS) faces persistent challenges in effectively leveraging unlabeled data, such as ineffective utilization of pseudo-labels, exacerbation of class imbalance biases, and neglect of prediction uncertainty. Current approaches often discard uncertain regions through strict thresholding favouring dominant classes. To address these limitations, we introduce a holistic framework that transforms uncertainty into a learning asset through four principal components: (1) fuzzy pseudo-labeling, which preserves soft class distributions from top-K predictions to enrich"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.11142","kind":"arxiv","version":2},"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/2506.11142/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":"2506.11142","created_at":"2026-07-05T11:25:45.895389+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.11142v2","created_at":"2026-07-05T11:25:45.895389+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11142","created_at":"2026-07-05T11:25:45.895389+00:00"},{"alias_kind":"pith_short_12","alias_value":"SUEZZVJBKXGT","created_at":"2026-07-05T11:25:45.895389+00:00"},{"alias_kind":"pith_short_16","alias_value":"SUEZZVJBKXGTMG6Q","created_at":"2026-07-05T11:25:45.895389+00:00"},{"alias_kind":"pith_short_8","alias_value":"SUEZZVJB","created_at":"2026-07-05T11:25:45.895389+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/SUEZZVJBKXGTMG6QDWSRVSKV2I","json":"https://pith.science/pith/SUEZZVJBKXGTMG6QDWSRVSKV2I.json","graph_json":"https://pith.science/api/pith-number/SUEZZVJBKXGTMG6QDWSRVSKV2I/graph.json","events_json":"https://pith.science/api/pith-number/SUEZZVJBKXGTMG6QDWSRVSKV2I/events.json","paper":"https://pith.science/paper/SUEZZVJB"},"agent_actions":{"view_html":"https://pith.science/pith/SUEZZVJBKXGTMG6QDWSRVSKV2I","download_json":"https://pith.science/pith/SUEZZVJBKXGTMG6QDWSRVSKV2I.json","view_paper":"https://pith.science/paper/SUEZZVJB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.11142&json=true","fetch_graph":"https://pith.science/api/pith-number/SUEZZVJBKXGTMG6QDWSRVSKV2I/graph.json","fetch_events":"https://pith.science/api/pith-number/SUEZZVJBKXGTMG6QDWSRVSKV2I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SUEZZVJBKXGTMG6QDWSRVSKV2I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SUEZZVJBKXGTMG6QDWSRVSKV2I/action/storage_attestation","attest_author":"https://pith.science/pith/SUEZZVJBKXGTMG6QDWSRVSKV2I/action/author_attestation","sign_citation":"https://pith.science/pith/SUEZZVJBKXGTMG6QDWSRVSKV2I/action/citation_signature","submit_replication":"https://pith.science/pith/SUEZZVJBKXGTMG6QDWSRVSKV2I/action/replication_record"}},"created_at":"2026-07-05T11:25:45.895389+00:00","updated_at":"2026-07-05T11:25:45.895389+00:00"}