{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:2XZBVP2MYXLEB3N4JGTM7TVYVI","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"a22584fe802396ece5af5654ff0592cc0e4d0fa68ea7526dd1ac1b23fde2d163","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-03T23:52:38Z","title_canon_sha256":"e9bd564f816faf879e4fd8b91252f4f370012595bbfc6da8f35cfef99b60536a"},"schema_version":"1.0","source":{"id":"2103.02761","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.02761","created_at":"2026-07-05T02:20:20Z"},{"alias_kind":"arxiv_version","alias_value":"2103.02761v1","created_at":"2026-07-05T02:20:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.02761","created_at":"2026-07-05T02:20:20Z"},{"alias_kind":"pith_short_12","alias_value":"2XZBVP2MYXLE","created_at":"2026-07-05T02:20:20Z"},{"alias_kind":"pith_short_16","alias_value":"2XZBVP2MYXLEB3N4","created_at":"2026-07-05T02:20:20Z"},{"alias_kind":"pith_short_8","alias_value":"2XZBVP2M","created_at":"2026-07-05T02:20:20Z"}],"graph_snapshots":[{"event_id":"sha256:b8ea96fa28b360f1738689e6b08dc829928439ff0f17c7dc563f235d792f917b","target":"graph","created_at":"2026-07-05T02:20:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2103.02761/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Labeling data for modern machine learning is expensive and time-consuming. Latent variable models can be used to infer labels from weaker, easier-to-acquire sources operating on unlabeled data. Such models can also be trained using labeled data, presenting a key question: should a user invest in few labeled or many unlabeled points? We answer this via a framework centered on model misspecification in method-of-moments latent variable estimation. Our core result is a bias-variance decomposition of the generalization error, which shows that the unlabeled-only approach incurs additional bias unde","authors_text":"Benjamin Cohen-Wang, Christopher R\\'e, Frederic Sala, Mayee F. Chen, Stephen Mussmann","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-03T23:52:38Z","title":"Comparing the Value of Labeled and Unlabeled Data in Method-of-Moments Latent Variable Estimation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.02761","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5dbc069d56e9f815a65dde2afff39fad0f6e3fd93b63b39f689553f978b19aaa","target":"record","created_at":"2026-07-05T02:20:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"a22584fe802396ece5af5654ff0592cc0e4d0fa68ea7526dd1ac1b23fde2d163","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-03T23:52:38Z","title_canon_sha256":"e9bd564f816faf879e4fd8b91252f4f370012595bbfc6da8f35cfef99b60536a"},"schema_version":"1.0","source":{"id":"2103.02761","kind":"arxiv","version":1}},"canonical_sha256":"d5f21abf4cc5d640edbc49a6cfceb8aa2be390ff422a3680f65b916bd9100519","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d5f21abf4cc5d640edbc49a6cfceb8aa2be390ff422a3680f65b916bd9100519","first_computed_at":"2026-07-05T02:20:20.781670Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:20:20.781670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0hSk8rP6OhAzV0rEWZM8PeiTyI91NPg1huVNxdghJPC0UYOm/4WJrdjWqY7GKk4eTsrsY77aeTbWYHqlB6+fCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:20:20.782088Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.02761","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5dbc069d56e9f815a65dde2afff39fad0f6e3fd93b63b39f689553f978b19aaa","sha256:b8ea96fa28b360f1738689e6b08dc829928439ff0f17c7dc563f235d792f917b"],"state_sha256":"e3cb959691529d0234cecf8ffdcdc24de1e3d86064a5b05029090c3c93995f41"}