{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PQAU7SZ3DQDGY2J6READGVXZ3K","short_pith_number":"pith:PQAU7SZ3","schema_version":"1.0","canonical_sha256":"7c014fcb3b1c066c693e89003356f9da827d2a97b51bb1c863f547b45eea82e5","source":{"kind":"arxiv","id":"2305.01747","version":2},"attestation_state":"computed","paper":{"title":"Expectation Maximization Pseudo Labels","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chen Jin, Daniel C. Alexander, Joseph Jacob, Marius de Groot, Moucheng Xu, Neil P. Oxtoby, Yipeng Hu, Yukun Zhou","submitted_at":"2023-05-02T19:29:17Z","abstract_excerpt":"In this paper, we study pseudo-labelling. Pseudo-labelling employs raw inferences on unlabelled data as pseudo-labels for self-training. We elucidate the empirical successes of pseudo-labelling by establishing a link between this technique and the Expectation Maximisation algorithm. Through this, we realise that the original pseudo-labelling serves as an empirical estimation of its more comprehensive underlying formulation. Following this insight, we present a full generalisation of pseudo-labels under Bayes' theorem, termed Bayesian Pseudo Labels. Subsequently, we introduce a variational appr"},"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":"2305.01747","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-02T19:29:17Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"11f485e9a91cc89b32545f08e0fd37b7bf616fef0e918f5323027be79f41ca25","abstract_canon_sha256":"337f180d1f03a5a87dc9313d50468c51d62f12a94a9aaea9651b89bd2bc43e1c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:37:49.433351Z","signature_b64":"2Pc3ZoTb7SsVXJ9ymu1n3hR4ah19wK15yrsddgaj6qNQfut1S8S+aJ7EmHvHMWr0ZjXs3R3bOtsZrlLeYkgMAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c014fcb3b1c066c693e89003356f9da827d2a97b51bb1c863f547b45eea82e5","last_reissued_at":"2026-07-05T07:37:49.432824Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:37:49.432824Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Expectation Maximization Pseudo Labels","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chen Jin, Daniel C. Alexander, Joseph Jacob, Marius de Groot, Moucheng Xu, Neil P. Oxtoby, Yipeng Hu, Yukun Zhou","submitted_at":"2023-05-02T19:29:17Z","abstract_excerpt":"In this paper, we study pseudo-labelling. Pseudo-labelling employs raw inferences on unlabelled data as pseudo-labels for self-training. We elucidate the empirical successes of pseudo-labelling by establishing a link between this technique and the Expectation Maximisation algorithm. Through this, we realise that the original pseudo-labelling serves as an empirical estimation of its more comprehensive underlying formulation. Following this insight, we present a full generalisation of pseudo-labels under Bayes' theorem, termed Bayesian Pseudo Labels. Subsequently, we introduce a variational appr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.01747","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/2305.01747/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":"2305.01747","created_at":"2026-07-05T07:37:49.432892+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.01747v2","created_at":"2026-07-05T07:37:49.432892+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.01747","created_at":"2026-07-05T07:37:49.432892+00:00"},{"alias_kind":"pith_short_12","alias_value":"PQAU7SZ3DQDG","created_at":"2026-07-05T07:37:49.432892+00:00"},{"alias_kind":"pith_short_16","alias_value":"PQAU7SZ3DQDGY2J6","created_at":"2026-07-05T07:37:49.432892+00:00"},{"alias_kind":"pith_short_8","alias_value":"PQAU7SZ3","created_at":"2026-07-05T07:37:49.432892+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/PQAU7SZ3DQDGY2J6READGVXZ3K","json":"https://pith.science/pith/PQAU7SZ3DQDGY2J6READGVXZ3K.json","graph_json":"https://pith.science/api/pith-number/PQAU7SZ3DQDGY2J6READGVXZ3K/graph.json","events_json":"https://pith.science/api/pith-number/PQAU7SZ3DQDGY2J6READGVXZ3K/events.json","paper":"https://pith.science/paper/PQAU7SZ3"},"agent_actions":{"view_html":"https://pith.science/pith/PQAU7SZ3DQDGY2J6READGVXZ3K","download_json":"https://pith.science/pith/PQAU7SZ3DQDGY2J6READGVXZ3K.json","view_paper":"https://pith.science/paper/PQAU7SZ3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.01747&json=true","fetch_graph":"https://pith.science/api/pith-number/PQAU7SZ3DQDGY2J6READGVXZ3K/graph.json","fetch_events":"https://pith.science/api/pith-number/PQAU7SZ3DQDGY2J6READGVXZ3K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PQAU7SZ3DQDGY2J6READGVXZ3K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PQAU7SZ3DQDGY2J6READGVXZ3K/action/storage_attestation","attest_author":"https://pith.science/pith/PQAU7SZ3DQDGY2J6READGVXZ3K/action/author_attestation","sign_citation":"https://pith.science/pith/PQAU7SZ3DQDGY2J6READGVXZ3K/action/citation_signature","submit_replication":"https://pith.science/pith/PQAU7SZ3DQDGY2J6READGVXZ3K/action/replication_record"}},"created_at":"2026-07-05T07:37:49.432892+00:00","updated_at":"2026-07-05T07:37:49.432892+00:00"}