{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MXMRBQ2YQR7WOIAKALT5IXH3AM","short_pith_number":"pith:MXMRBQ2Y","schema_version":"1.0","canonical_sha256":"65d910c358847f67200a02e7d45cfb0313c62728146881b1aa4445d4332a3d61","source":{"kind":"arxiv","id":"2502.00279","version":1},"attestation_state":"computed","paper":{"title":"Improving realistic semi-supervised learning with doubly robust estimation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Charles Herrmann, Khiem Pham, Ramin Zabih","submitted_at":"2025-02-01T02:34:12Z","abstract_excerpt":"A major challenge in Semi-Supervised Learning (SSL) is the limited information available about the class distribution in the unlabeled data. In many real-world applications this arises from the prevalence of long-tailed distributions, where the standard pseudo-label approach to SSL is biased towards the labeled class distribution and thus performs poorly on unlabeled data. Existing methods typically assume that the unlabeled class distribution is either known a priori, which is unrealistic in most situations, or estimate it on-the-fly using the pseudo-labels themselves. We propose to explicitl"},"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":"2502.00279","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-01T02:34:12Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"509167ba7c1829137b35e8237bda604f57bb7314861d56eeb04863852c78bc72","abstract_canon_sha256":"088531bd499e622e21b72e90f40626604707ae0d3df9bcbe2ae9ee992af3c5d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:08:31.662301Z","signature_b64":"mnpqSW45jgatZQA1+o+sM0kg/B0DflQNYYNdUfWK5tSK5cwnu0L6exjtg2w9V0+EfyeXGdHbKx2tl1FMgOf1Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65d910c358847f67200a02e7d45cfb0313c62728146881b1aa4445d4332a3d61","last_reissued_at":"2026-07-05T10:08:31.661807Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:08:31.661807Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving realistic semi-supervised learning with doubly robust estimation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Charles Herrmann, Khiem Pham, Ramin Zabih","submitted_at":"2025-02-01T02:34:12Z","abstract_excerpt":"A major challenge in Semi-Supervised Learning (SSL) is the limited information available about the class distribution in the unlabeled data. In many real-world applications this arises from the prevalence of long-tailed distributions, where the standard pseudo-label approach to SSL is biased towards the labeled class distribution and thus performs poorly on unlabeled data. Existing methods typically assume that the unlabeled class distribution is either known a priori, which is unrealistic in most situations, or estimate it on-the-fly using the pseudo-labels themselves. We propose to explicitl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.00279","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/2502.00279/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":"2502.00279","created_at":"2026-07-05T10:08:31.661868+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.00279v1","created_at":"2026-07-05T10:08:31.661868+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.00279","created_at":"2026-07-05T10:08:31.661868+00:00"},{"alias_kind":"pith_short_12","alias_value":"MXMRBQ2YQR7W","created_at":"2026-07-05T10:08:31.661868+00:00"},{"alias_kind":"pith_short_16","alias_value":"MXMRBQ2YQR7WOIAK","created_at":"2026-07-05T10:08:31.661868+00:00"},{"alias_kind":"pith_short_8","alias_value":"MXMRBQ2Y","created_at":"2026-07-05T10:08:31.661868+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/MXMRBQ2YQR7WOIAKALT5IXH3AM","json":"https://pith.science/pith/MXMRBQ2YQR7WOIAKALT5IXH3AM.json","graph_json":"https://pith.science/api/pith-number/MXMRBQ2YQR7WOIAKALT5IXH3AM/graph.json","events_json":"https://pith.science/api/pith-number/MXMRBQ2YQR7WOIAKALT5IXH3AM/events.json","paper":"https://pith.science/paper/MXMRBQ2Y"},"agent_actions":{"view_html":"https://pith.science/pith/MXMRBQ2YQR7WOIAKALT5IXH3AM","download_json":"https://pith.science/pith/MXMRBQ2YQR7WOIAKALT5IXH3AM.json","view_paper":"https://pith.science/paper/MXMRBQ2Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.00279&json=true","fetch_graph":"https://pith.science/api/pith-number/MXMRBQ2YQR7WOIAKALT5IXH3AM/graph.json","fetch_events":"https://pith.science/api/pith-number/MXMRBQ2YQR7WOIAKALT5IXH3AM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MXMRBQ2YQR7WOIAKALT5IXH3AM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MXMRBQ2YQR7WOIAKALT5IXH3AM/action/storage_attestation","attest_author":"https://pith.science/pith/MXMRBQ2YQR7WOIAKALT5IXH3AM/action/author_attestation","sign_citation":"https://pith.science/pith/MXMRBQ2YQR7WOIAKALT5IXH3AM/action/citation_signature","submit_replication":"https://pith.science/pith/MXMRBQ2YQR7WOIAKALT5IXH3AM/action/replication_record"}},"created_at":"2026-07-05T10:08:31.661868+00:00","updated_at":"2026-07-05T10:08:31.661868+00:00"}