{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ELSQ2ZZDKXXWBCEQ6VREXC4FM4","short_pith_number":"pith:ELSQ2ZZD","schema_version":"1.0","canonical_sha256":"22e50d672355ef608890f5624b8b8567283252cafee073de84d1bc2b019653a6","source":{"kind":"arxiv","id":"2206.14261","version":2},"attestation_state":"computed","paper":{"title":"Semi-supervised Contrastive Outlier removal for Pseudo Expectation Maximization (SCOPE)","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"David Chapman, Sumeet Menon","submitted_at":"2022-06-28T19:32:50Z","abstract_excerpt":"Semi-supervised learning is the problem of training an accurate predictive model by combining a small labeled dataset with a presumably much larger unlabeled dataset. Many methods for semi-supervised deep learning have been developed, including pseudolabeling, consistency regularization, and contrastive learning techniques. Pseudolabeling methods however are highly susceptible to confounding, in which erroneous pseudolabels are assumed to be true labels in early iterations, thereby causing the model to reinforce its prior biases and thereby fail to generalize to strong predictive performance. "},"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":"2206.14261","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-28T19:32:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"29233e0310dd04ea16035178cc4b74648085d1242c08c76ebc0594fc0ba97c9b","abstract_canon_sha256":"f97fba27e62ba2785b70bb4c265f6a3ba9b0b416970911534a3d350e6c59d11d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:06:00.737872Z","signature_b64":"vbBdoj7FiGMBuAhmyU0aLRxvSKZ/PaezdVWG4zaNT8pyDRlsaLPeD5DfNb3JKeWMt+VDXeAXNQrMWQfAgjtNBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"22e50d672355ef608890f5624b8b8567283252cafee073de84d1bc2b019653a6","last_reissued_at":"2026-07-05T07:06:00.737420Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:06:00.737420Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semi-supervised Contrastive Outlier removal for Pseudo Expectation Maximization (SCOPE)","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"David Chapman, Sumeet Menon","submitted_at":"2022-06-28T19:32:50Z","abstract_excerpt":"Semi-supervised learning is the problem of training an accurate predictive model by combining a small labeled dataset with a presumably much larger unlabeled dataset. Many methods for semi-supervised deep learning have been developed, including pseudolabeling, consistency regularization, and contrastive learning techniques. Pseudolabeling methods however are highly susceptible to confounding, in which erroneous pseudolabels are assumed to be true labels in early iterations, thereby causing the model to reinforce its prior biases and thereby fail to generalize to strong predictive performance. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.14261","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/2206.14261/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":"2206.14261","created_at":"2026-07-05T07:06:00.737478+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.14261v2","created_at":"2026-07-05T07:06:00.737478+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.14261","created_at":"2026-07-05T07:06:00.737478+00:00"},{"alias_kind":"pith_short_12","alias_value":"ELSQ2ZZDKXXW","created_at":"2026-07-05T07:06:00.737478+00:00"},{"alias_kind":"pith_short_16","alias_value":"ELSQ2ZZDKXXWBCEQ","created_at":"2026-07-05T07:06:00.737478+00:00"},{"alias_kind":"pith_short_8","alias_value":"ELSQ2ZZD","created_at":"2026-07-05T07:06:00.737478+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/ELSQ2ZZDKXXWBCEQ6VREXC4FM4","json":"https://pith.science/pith/ELSQ2ZZDKXXWBCEQ6VREXC4FM4.json","graph_json":"https://pith.science/api/pith-number/ELSQ2ZZDKXXWBCEQ6VREXC4FM4/graph.json","events_json":"https://pith.science/api/pith-number/ELSQ2ZZDKXXWBCEQ6VREXC4FM4/events.json","paper":"https://pith.science/paper/ELSQ2ZZD"},"agent_actions":{"view_html":"https://pith.science/pith/ELSQ2ZZDKXXWBCEQ6VREXC4FM4","download_json":"https://pith.science/pith/ELSQ2ZZDKXXWBCEQ6VREXC4FM4.json","view_paper":"https://pith.science/paper/ELSQ2ZZD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.14261&json=true","fetch_graph":"https://pith.science/api/pith-number/ELSQ2ZZDKXXWBCEQ6VREXC4FM4/graph.json","fetch_events":"https://pith.science/api/pith-number/ELSQ2ZZDKXXWBCEQ6VREXC4FM4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ELSQ2ZZDKXXWBCEQ6VREXC4FM4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ELSQ2ZZDKXXWBCEQ6VREXC4FM4/action/storage_attestation","attest_author":"https://pith.science/pith/ELSQ2ZZDKXXWBCEQ6VREXC4FM4/action/author_attestation","sign_citation":"https://pith.science/pith/ELSQ2ZZDKXXWBCEQ6VREXC4FM4/action/citation_signature","submit_replication":"https://pith.science/pith/ELSQ2ZZDKXXWBCEQ6VREXC4FM4/action/replication_record"}},"created_at":"2026-07-05T07:06:00.737478+00:00","updated_at":"2026-07-05T07:06:00.737478+00:00"}