{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:TNHQJZ7IPBPFEW3BRDELJBLVZ6","short_pith_number":"pith:TNHQJZ7I","schema_version":"1.0","canonical_sha256":"9b4f04e7e8785e525b6188c8b48575cfbf3f002416f5f242b07c6402d9581aa2","source":{"kind":"arxiv","id":"2207.12131","version":1},"attestation_state":"computed","paper":{"title":"Complementing Semi-Supervised Learning with Uncertainty Quantification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ehsan Kazemi","submitted_at":"2022-07-22T00:15:02Z","abstract_excerpt":"The problem of fully supervised classification is that it requires a tremendous amount of annotated data, however, in many datasets a large portion of data is unlabeled. To alleviate this problem semi-supervised learning (SSL) leverages the knowledge of the classifier on the labeled domain and extrapolates it to the unlabeled domain which has a supposedly similar distribution as annotated data. Recent success on SSL methods crucially hinges on thresholded pseudo labeling and thereby consistency regularization for the unlabeled domain. However, the existing methods do not incorporate the uncert"},"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":"2207.12131","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-22T00:15:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"66f3e384fc7223e0ef5ebec8264bcf555d98a74a455fee23a1392f7da684a227","abstract_canon_sha256":"04992f4d30592280cb24e3a70efb289ff80fb7242c39fd84c453ae4f6b40feeb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:43:13.629435Z","signature_b64":"LpIzaKC2rBfp6wWmawObAxW1osOxh6QIdTG7y92tYg87eHcTIorQO0laU5lyk6n8vQFAi5TWy9zKiL0PHqYpCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b4f04e7e8785e525b6188c8b48575cfbf3f002416f5f242b07c6402d9581aa2","last_reissued_at":"2026-07-05T04:43:13.629075Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:43:13.629075Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Complementing Semi-Supervised Learning with Uncertainty Quantification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ehsan Kazemi","submitted_at":"2022-07-22T00:15:02Z","abstract_excerpt":"The problem of fully supervised classification is that it requires a tremendous amount of annotated data, however, in many datasets a large portion of data is unlabeled. To alleviate this problem semi-supervised learning (SSL) leverages the knowledge of the classifier on the labeled domain and extrapolates it to the unlabeled domain which has a supposedly similar distribution as annotated data. Recent success on SSL methods crucially hinges on thresholded pseudo labeling and thereby consistency regularization for the unlabeled domain. However, the existing methods do not incorporate the uncert"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.12131","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/2207.12131/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":"2207.12131","created_at":"2026-07-05T04:43:13.629130+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.12131v1","created_at":"2026-07-05T04:43:13.629130+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.12131","created_at":"2026-07-05T04:43:13.629130+00:00"},{"alias_kind":"pith_short_12","alias_value":"TNHQJZ7IPBPF","created_at":"2026-07-05T04:43:13.629130+00:00"},{"alias_kind":"pith_short_16","alias_value":"TNHQJZ7IPBPFEW3B","created_at":"2026-07-05T04:43:13.629130+00:00"},{"alias_kind":"pith_short_8","alias_value":"TNHQJZ7I","created_at":"2026-07-05T04:43:13.629130+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.19906","citing_title":"Streamlining the Development of Active Learning Methods in Real-World Object Detection","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TNHQJZ7IPBPFEW3BRDELJBLVZ6","json":"https://pith.science/pith/TNHQJZ7IPBPFEW3BRDELJBLVZ6.json","graph_json":"https://pith.science/api/pith-number/TNHQJZ7IPBPFEW3BRDELJBLVZ6/graph.json","events_json":"https://pith.science/api/pith-number/TNHQJZ7IPBPFEW3BRDELJBLVZ6/events.json","paper":"https://pith.science/paper/TNHQJZ7I"},"agent_actions":{"view_html":"https://pith.science/pith/TNHQJZ7IPBPFEW3BRDELJBLVZ6","download_json":"https://pith.science/pith/TNHQJZ7IPBPFEW3BRDELJBLVZ6.json","view_paper":"https://pith.science/paper/TNHQJZ7I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.12131&json=true","fetch_graph":"https://pith.science/api/pith-number/TNHQJZ7IPBPFEW3BRDELJBLVZ6/graph.json","fetch_events":"https://pith.science/api/pith-number/TNHQJZ7IPBPFEW3BRDELJBLVZ6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TNHQJZ7IPBPFEW3BRDELJBLVZ6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TNHQJZ7IPBPFEW3BRDELJBLVZ6/action/storage_attestation","attest_author":"https://pith.science/pith/TNHQJZ7IPBPFEW3BRDELJBLVZ6/action/author_attestation","sign_citation":"https://pith.science/pith/TNHQJZ7IPBPFEW3BRDELJBLVZ6/action/citation_signature","submit_replication":"https://pith.science/pith/TNHQJZ7IPBPFEW3BRDELJBLVZ6/action/replication_record"}},"created_at":"2026-07-05T04:43:13.629130+00:00","updated_at":"2026-07-05T04:43:13.629130+00:00"}