{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:BQHKRNVCEWGKBUQ3AGK76MX4MD","short_pith_number":"pith:BQHKRNVC","schema_version":"1.0","canonical_sha256":"0c0ea8b6a2258ca0d21b0195ff32fc60f9046fd7f3164ebed6d9544415aea1e2","source":{"kind":"arxiv","id":"2206.06959","version":1},"attestation_state":"computed","paper":{"title":"AuxMix: Semi-Supervised Learning with Unconstrained Unlabeled Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Amin Banitalebi-Dehkordi, Pratik Gujjar, Yong Zhang","submitted_at":"2022-06-14T16:25:20Z","abstract_excerpt":"Semi-supervised learning (SSL) has seen great strides when labeled data is scarce but unlabeled data is abundant. Critically, most recent work assume that such unlabeled data is drawn from the same distribution as the labeled data. In this work, we show that state-of-the-art SSL algorithms suffer a degradation in performance in the presence of unlabeled auxiliary data that does not necessarily possess the same class distribution as the labeled set. We term this problem as Auxiliary-SSL and propose AuxMix, an algorithm that leverages self-supervised learning tasks to learn generic features in o"},"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":"2206.06959","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-14T16:25:20Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"825f07ee56c7ad5e2f3c3534c489f97c754814ed8ee9c975d97132ef619c7ab6","abstract_canon_sha256":"1e1343895a3d1c7c469f0a9c2ce100772832a3eba9d735b4e9d4fb75aff69d5d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:31:47.672710Z","signature_b64":"QnbHfFtjdCsW0sn9qV6Sgh+6PYGdixPqFLMHk1h6d2xyJrUYwvTC60URCqoBHpnXz/WvZ6xqw4P6UGfLJ3fdBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c0ea8b6a2258ca0d21b0195ff32fc60f9046fd7f3164ebed6d9544415aea1e2","last_reissued_at":"2026-07-05T04:31:47.672216Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:31:47.672216Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AuxMix: Semi-Supervised Learning with Unconstrained Unlabeled Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Amin Banitalebi-Dehkordi, Pratik Gujjar, Yong Zhang","submitted_at":"2022-06-14T16:25:20Z","abstract_excerpt":"Semi-supervised learning (SSL) has seen great strides when labeled data is scarce but unlabeled data is abundant. Critically, most recent work assume that such unlabeled data is drawn from the same distribution as the labeled data. In this work, we show that state-of-the-art SSL algorithms suffer a degradation in performance in the presence of unlabeled auxiliary data that does not necessarily possess the same class distribution as the labeled set. We term this problem as Auxiliary-SSL and propose AuxMix, an algorithm that leverages self-supervised learning tasks to learn generic features in o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.06959","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/2206.06959/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":"2206.06959","created_at":"2026-07-05T04:31:47.672277+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.06959v1","created_at":"2026-07-05T04:31:47.672277+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.06959","created_at":"2026-07-05T04:31:47.672277+00:00"},{"alias_kind":"pith_short_12","alias_value":"BQHKRNVCEWGK","created_at":"2026-07-05T04:31:47.672277+00:00"},{"alias_kind":"pith_short_16","alias_value":"BQHKRNVCEWGKBUQ3","created_at":"2026-07-05T04:31:47.672277+00:00"},{"alias_kind":"pith_short_8","alias_value":"BQHKRNVC","created_at":"2026-07-05T04:31:47.672277+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.18593","citing_title":"Severity Classification of Chronic Obstructive Pulmonary Disease in Intensive Care Units: A Semi-Supervised Approach Using MIMIC-III Dataset","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BQHKRNVCEWGKBUQ3AGK76MX4MD","json":"https://pith.science/pith/BQHKRNVCEWGKBUQ3AGK76MX4MD.json","graph_json":"https://pith.science/api/pith-number/BQHKRNVCEWGKBUQ3AGK76MX4MD/graph.json","events_json":"https://pith.science/api/pith-number/BQHKRNVCEWGKBUQ3AGK76MX4MD/events.json","paper":"https://pith.science/paper/BQHKRNVC"},"agent_actions":{"view_html":"https://pith.science/pith/BQHKRNVCEWGKBUQ3AGK76MX4MD","download_json":"https://pith.science/pith/BQHKRNVCEWGKBUQ3AGK76MX4MD.json","view_paper":"https://pith.science/paper/BQHKRNVC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.06959&json=true","fetch_graph":"https://pith.science/api/pith-number/BQHKRNVCEWGKBUQ3AGK76MX4MD/graph.json","fetch_events":"https://pith.science/api/pith-number/BQHKRNVCEWGKBUQ3AGK76MX4MD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BQHKRNVCEWGKBUQ3AGK76MX4MD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BQHKRNVCEWGKBUQ3AGK76MX4MD/action/storage_attestation","attest_author":"https://pith.science/pith/BQHKRNVCEWGKBUQ3AGK76MX4MD/action/author_attestation","sign_citation":"https://pith.science/pith/BQHKRNVCEWGKBUQ3AGK76MX4MD/action/citation_signature","submit_replication":"https://pith.science/pith/BQHKRNVCEWGKBUQ3AGK76MX4MD/action/replication_record"}},"created_at":"2026-07-05T04:31:47.672277+00:00","updated_at":"2026-07-05T04:31:47.672277+00:00"}