{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:3XKOW37ZLEBQWEYA2YZFUAZ5K5","short_pith_number":"pith:3XKOW37Z","schema_version":"1.0","canonical_sha256":"ddd4eb6ff959030b1300d6325a033d57436779209e686444ef37c7966d38f121","source":{"kind":"arxiv","id":"2208.07204","version":2},"attestation_state":"computed","paper":{"title":"USB: A Unified Semi-supervised Learning Benchmark for Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Bernt Schiele, Bhiksha Raj, Hao Chen, Heli Qi, Jindong Wang, Lan-Zhe Guo, Linyi Yang, Marios Savvides, Ran Tao, Renjie Wang, Satoshi Nakamura, Takahiro Shinozaki, Wang Sun, Wei Ye, Wenxin Hou, Xing Xie, Yidong Wang, Yue Fan, Yue Zhang, Yu-Feng Li, Zhen Wu, Zhi Zhou","submitted_at":"2022-08-12T15:45:48Z","abstract_excerpt":"Semi-supervised learning (SSL) improves model generalization by leveraging massive unlabeled data to augment limited labeled samples. However, currently, popular SSL evaluation protocols are often constrained to computer vision (CV) tasks. In addition, previous work typically trains deep neural networks from scratch, which is time-consuming and environmentally unfriendly. To address the above issues, we construct a Unified SSL Benchmark (USB) for classification by selecting 15 diverse, challenging, and comprehensive tasks from CV, natural language processing (NLP), and audio processing (Audio)"},"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":"2208.07204","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-08-12T15:45:48Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"3f53e84a4a6cd9f69931265bc73332e4c856d9f9bf73bb941dde904b47a5f21d","abstract_canon_sha256":"ef9be06fa25ebe179f6ae54f711fa77db036f7dc242aef4b069ca32491c3d13c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:06:33.494968Z","signature_b64":"VgwTETSlPlf5oybwpgvrd6AgV1pUcy03l1RohnxvC0hDizLNKSL7uKG+1XVl8IPZpUp59l8hN2ZZfIfdRuNeBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ddd4eb6ff959030b1300d6325a033d57436779209e686444ef37c7966d38f121","last_reissued_at":"2026-07-05T05:06:33.494413Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:06:33.494413Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"USB: A Unified Semi-supervised Learning Benchmark for Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Bernt Schiele, Bhiksha Raj, Hao Chen, Heli Qi, Jindong Wang, Lan-Zhe Guo, Linyi Yang, Marios Savvides, Ran Tao, Renjie Wang, Satoshi Nakamura, Takahiro Shinozaki, Wang Sun, Wei Ye, Wenxin Hou, Xing Xie, Yidong Wang, Yue Fan, Yue Zhang, Yu-Feng Li, Zhen Wu, Zhi Zhou","submitted_at":"2022-08-12T15:45:48Z","abstract_excerpt":"Semi-supervised learning (SSL) improves model generalization by leveraging massive unlabeled data to augment limited labeled samples. However, currently, popular SSL evaluation protocols are often constrained to computer vision (CV) tasks. In addition, previous work typically trains deep neural networks from scratch, which is time-consuming and environmentally unfriendly. To address the above issues, we construct a Unified SSL Benchmark (USB) for classification by selecting 15 diverse, challenging, and comprehensive tasks from CV, natural language processing (NLP), and audio processing (Audio)"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.07204","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/2208.07204/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":"2208.07204","created_at":"2026-07-05T05:06:33.494519+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.07204v2","created_at":"2026-07-05T05:06:33.494519+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.07204","created_at":"2026-07-05T05:06:33.494519+00:00"},{"alias_kind":"pith_short_12","alias_value":"3XKOW37ZLEBQ","created_at":"2026-07-05T05:06:33.494519+00:00"},{"alias_kind":"pith_short_16","alias_value":"3XKOW37ZLEBQWEYA","created_at":"2026-07-05T05:06:33.494519+00:00"},{"alias_kind":"pith_short_8","alias_value":"3XKOW37Z","created_at":"2026-07-05T05:06:33.494519+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26973","citing_title":"Geometric Gradient Rectification for Safe Open-Set Semi-Supervised Learning","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3XKOW37ZLEBQWEYA2YZFUAZ5K5","json":"https://pith.science/pith/3XKOW37ZLEBQWEYA2YZFUAZ5K5.json","graph_json":"https://pith.science/api/pith-number/3XKOW37ZLEBQWEYA2YZFUAZ5K5/graph.json","events_json":"https://pith.science/api/pith-number/3XKOW37ZLEBQWEYA2YZFUAZ5K5/events.json","paper":"https://pith.science/paper/3XKOW37Z"},"agent_actions":{"view_html":"https://pith.science/pith/3XKOW37ZLEBQWEYA2YZFUAZ5K5","download_json":"https://pith.science/pith/3XKOW37ZLEBQWEYA2YZFUAZ5K5.json","view_paper":"https://pith.science/paper/3XKOW37Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.07204&json=true","fetch_graph":"https://pith.science/api/pith-number/3XKOW37ZLEBQWEYA2YZFUAZ5K5/graph.json","fetch_events":"https://pith.science/api/pith-number/3XKOW37ZLEBQWEYA2YZFUAZ5K5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3XKOW37ZLEBQWEYA2YZFUAZ5K5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3XKOW37ZLEBQWEYA2YZFUAZ5K5/action/storage_attestation","attest_author":"https://pith.science/pith/3XKOW37ZLEBQWEYA2YZFUAZ5K5/action/author_attestation","sign_citation":"https://pith.science/pith/3XKOW37ZLEBQWEYA2YZFUAZ5K5/action/citation_signature","submit_replication":"https://pith.science/pith/3XKOW37ZLEBQWEYA2YZFUAZ5K5/action/replication_record"}},"created_at":"2026-07-05T05:06:33.494519+00:00","updated_at":"2026-07-05T05:06:33.494519+00:00"}