{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:4WLXANW3O24CTCJ3NWWFWSQKOA","short_pith_number":"pith:4WLXANW3","schema_version":"1.0","canonical_sha256":"e5977036db76b829893b6dac5b4a0a7011ddb425f88aec78cfcad0fd72330194","source":{"kind":"arxiv","id":"2112.03865","version":3},"attestation_state":"computed","paper":{"title":"Universalizing Weak Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Changho Shin, Frederic Sala, Harit Vishwakarma, Nicholas Roberts, Winfred Li","submitted_at":"2021-12-07T17:59:10Z","abstract_excerpt":"Weak supervision (WS) frameworks are a popular way to bypass hand-labeling large datasets for training data-hungry models. These approaches synthesize multiple noisy but cheaply-acquired estimates of labels into a set of high-quality pseudolabels for downstream training. However, the synthesis technique is specific to a particular kind of label, such as binary labels or sequences, and each new label type requires manually designing a new synthesis algorithm. Instead, we propose a universal technique that enables weak supervision over any label type while still offering desirable properties, in"},"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":"2112.03865","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-07T17:59:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"63b49988970147e1bb6bfaea5f4c4bae9518e8cc4fdebe485a0c53a1383654f5","abstract_canon_sha256":"926f91315b1bd4e77e97d291669d95ccc8823ad6912fff92c4339d843c2b7e32"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:18:07.819461Z","signature_b64":"RCqBgSEs715lirrdqVUE9Xdlh3CIZFCqkJauUEKksmszzaFjuwz9p1e7Jaru6sU6c3mrzzLiJHHv6Bfg/0uwBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e5977036db76b829893b6dac5b4a0a7011ddb425f88aec78cfcad0fd72330194","last_reissued_at":"2026-07-05T07:18:07.818925Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:18:07.818925Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Universalizing Weak Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Changho Shin, Frederic Sala, Harit Vishwakarma, Nicholas Roberts, Winfred Li","submitted_at":"2021-12-07T17:59:10Z","abstract_excerpt":"Weak supervision (WS) frameworks are a popular way to bypass hand-labeling large datasets for training data-hungry models. These approaches synthesize multiple noisy but cheaply-acquired estimates of labels into a set of high-quality pseudolabels for downstream training. However, the synthesis technique is specific to a particular kind of label, such as binary labels or sequences, and each new label type requires manually designing a new synthesis algorithm. Instead, we propose a universal technique that enables weak supervision over any label type while still offering desirable properties, in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.03865","kind":"arxiv","version":3},"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/2112.03865/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":"2112.03865","created_at":"2026-07-05T07:18:07.818985+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.03865v3","created_at":"2026-07-05T07:18:07.818985+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.03865","created_at":"2026-07-05T07:18:07.818985+00:00"},{"alias_kind":"pith_short_12","alias_value":"4WLXANW3O24C","created_at":"2026-07-05T07:18:07.818985+00:00"},{"alias_kind":"pith_short_16","alias_value":"4WLXANW3O24CTCJ3","created_at":"2026-07-05T07:18:07.818985+00:00"},{"alias_kind":"pith_short_8","alias_value":"4WLXANW3","created_at":"2026-07-05T07:18:07.818985+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.05002","citing_title":"Learning Stable Predictors from Weak Supervision under Distribution Shift","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05002","citing_title":"Learning Stable Predictors from Weak Supervision under Distribution Shift","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4WLXANW3O24CTCJ3NWWFWSQKOA","json":"https://pith.science/pith/4WLXANW3O24CTCJ3NWWFWSQKOA.json","graph_json":"https://pith.science/api/pith-number/4WLXANW3O24CTCJ3NWWFWSQKOA/graph.json","events_json":"https://pith.science/api/pith-number/4WLXANW3O24CTCJ3NWWFWSQKOA/events.json","paper":"https://pith.science/paper/4WLXANW3"},"agent_actions":{"view_html":"https://pith.science/pith/4WLXANW3O24CTCJ3NWWFWSQKOA","download_json":"https://pith.science/pith/4WLXANW3O24CTCJ3NWWFWSQKOA.json","view_paper":"https://pith.science/paper/4WLXANW3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.03865&json=true","fetch_graph":"https://pith.science/api/pith-number/4WLXANW3O24CTCJ3NWWFWSQKOA/graph.json","fetch_events":"https://pith.science/api/pith-number/4WLXANW3O24CTCJ3NWWFWSQKOA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4WLXANW3O24CTCJ3NWWFWSQKOA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4WLXANW3O24CTCJ3NWWFWSQKOA/action/storage_attestation","attest_author":"https://pith.science/pith/4WLXANW3O24CTCJ3NWWFWSQKOA/action/author_attestation","sign_citation":"https://pith.science/pith/4WLXANW3O24CTCJ3NWWFWSQKOA/action/citation_signature","submit_replication":"https://pith.science/pith/4WLXANW3O24CTCJ3NWWFWSQKOA/action/replication_record"}},"created_at":"2026-07-05T07:18:07.818985+00:00","updated_at":"2026-07-05T07:18:07.818985+00:00"}