{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:K4BUF6SKSB2BFHWM6QBNKCCERI","short_pith_number":"pith:K4BUF6SK","schema_version":"1.0","canonical_sha256":"570342fa4a9074129eccf402d508448a1cb4efd407769701a2e2c367ffb88b87","source":{"kind":"arxiv","id":"2211.11086","version":2},"attestation_state":"computed","paper":{"title":"An Embarrassingly Simple Baseline for Imbalanced Semi-Supervised Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Bernt Schiele, Bhiksha Raj, Hao Chen, Jindong Wang, Marios Savvides, Xing Xie, Yidong Wang, Yue Fan","submitted_at":"2022-11-20T21:18:41Z","abstract_excerpt":"Semi-supervised learning (SSL) has shown great promise in leveraging unlabeled data to improve model performance. While standard SSL assumes uniform data distribution, we consider a more realistic and challenging setting called imbalanced SSL, where imbalanced class distributions occur in both labeled and unlabeled data. Although there are existing endeavors to tackle this challenge, their performance degenerates when facing severe imbalance since they can not reduce the class imbalance sufficiently and effectively. In this paper, we study a simple yet overlooked baseline -- SimiS -- which tac"},"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":"2211.11086","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-20T21:18:41Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"5337c139ffb55432055301a9865c9547be7ba11ea62b6ac8a80f7c0c8d38c6c7","abstract_canon_sha256":"9f597c0af63d68445b2be56f1e4026fb1398f8a68360e0dceb15ef764494ee3c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:34:46.069686Z","signature_b64":"vApdrq1NQIrTX5+guPLpsa4Qcjt5wuSsKueo2hqA6TBUBQEumU+CwhcqCm+vhekpcHGY26deB5iA0q8+W9wpAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"570342fa4a9074129eccf402d508448a1cb4efd407769701a2e2c367ffb88b87","last_reissued_at":"2026-07-05T07:34:46.069236Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:34:46.069236Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Embarrassingly Simple Baseline for Imbalanced Semi-Supervised Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Bernt Schiele, Bhiksha Raj, Hao Chen, Jindong Wang, Marios Savvides, Xing Xie, Yidong Wang, Yue Fan","submitted_at":"2022-11-20T21:18:41Z","abstract_excerpt":"Semi-supervised learning (SSL) has shown great promise in leveraging unlabeled data to improve model performance. While standard SSL assumes uniform data distribution, we consider a more realistic and challenging setting called imbalanced SSL, where imbalanced class distributions occur in both labeled and unlabeled data. Although there are existing endeavors to tackle this challenge, their performance degenerates when facing severe imbalance since they can not reduce the class imbalance sufficiently and effectively. In this paper, we study a simple yet overlooked baseline -- SimiS -- which tac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.11086","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/2211.11086/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":"2211.11086","created_at":"2026-07-05T07:34:46.069290+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.11086v2","created_at":"2026-07-05T07:34:46.069290+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.11086","created_at":"2026-07-05T07:34:46.069290+00:00"},{"alias_kind":"pith_short_12","alias_value":"K4BUF6SKSB2B","created_at":"2026-07-05T07:34:46.069290+00:00"},{"alias_kind":"pith_short_16","alias_value":"K4BUF6SKSB2BFHWM","created_at":"2026-07-05T07:34:46.069290+00:00"},{"alias_kind":"pith_short_8","alias_value":"K4BUF6SK","created_at":"2026-07-05T07:34:46.069290+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.03997","citing_title":"JanusNet: Hierarchical Slice-Block Shuffle and Displacement for Semi-Supervised 3D Multi-Organ Segmentation","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K4BUF6SKSB2BFHWM6QBNKCCERI","json":"https://pith.science/pith/K4BUF6SKSB2BFHWM6QBNKCCERI.json","graph_json":"https://pith.science/api/pith-number/K4BUF6SKSB2BFHWM6QBNKCCERI/graph.json","events_json":"https://pith.science/api/pith-number/K4BUF6SKSB2BFHWM6QBNKCCERI/events.json","paper":"https://pith.science/paper/K4BUF6SK"},"agent_actions":{"view_html":"https://pith.science/pith/K4BUF6SKSB2BFHWM6QBNKCCERI","download_json":"https://pith.science/pith/K4BUF6SKSB2BFHWM6QBNKCCERI.json","view_paper":"https://pith.science/paper/K4BUF6SK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.11086&json=true","fetch_graph":"https://pith.science/api/pith-number/K4BUF6SKSB2BFHWM6QBNKCCERI/graph.json","fetch_events":"https://pith.science/api/pith-number/K4BUF6SKSB2BFHWM6QBNKCCERI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K4BUF6SKSB2BFHWM6QBNKCCERI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K4BUF6SKSB2BFHWM6QBNKCCERI/action/storage_attestation","attest_author":"https://pith.science/pith/K4BUF6SKSB2BFHWM6QBNKCCERI/action/author_attestation","sign_citation":"https://pith.science/pith/K4BUF6SKSB2BFHWM6QBNKCCERI/action/citation_signature","submit_replication":"https://pith.science/pith/K4BUF6SKSB2BFHWM6QBNKCCERI/action/replication_record"}},"created_at":"2026-07-05T07:34:46.069290+00:00","updated_at":"2026-07-05T07:34:46.069290+00:00"}