{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:RDVPJOX5OY7IX53Q6BPZPB2UYX","short_pith_number":"pith:RDVPJOX5","canonical_record":{"source":{"id":"1903.05844","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-03-14T07:55:52Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0a2284b59d8ca046144ca3b4ac36d228a27dae94cc2d59de053cd1786cce6611","abstract_canon_sha256":"5ee93d6f8cc359f670dc4be51f1b6d6813a25539d7ddf06e75a49f9864119e40"},"schema_version":"1.0"},"canonical_sha256":"88eaf4bafd763e8bf770f05f978754c5c904c8c059014dd854eaad832294ffb6","source":{"kind":"arxiv","id":"1903.05844","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.05844","created_at":"2026-05-17T23:51:16Z"},{"alias_kind":"arxiv_version","alias_value":"1903.05844v1","created_at":"2026-05-17T23:51:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.05844","created_at":"2026-05-17T23:51:16Z"},{"alias_kind":"pith_short_12","alias_value":"RDVPJOX5OY7I","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"RDVPJOX5OY7IX53Q","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"RDVPJOX5","created_at":"2026-05-18T12:33:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:RDVPJOX5OY7IX53Q6BPZPB2UYX","target":"record","payload":{"canonical_record":{"source":{"id":"1903.05844","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-03-14T07:55:52Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0a2284b59d8ca046144ca3b4ac36d228a27dae94cc2d59de053cd1786cce6611","abstract_canon_sha256":"5ee93d6f8cc359f670dc4be51f1b6d6813a25539d7ddf06e75a49f9864119e40"},"schema_version":"1.0"},"canonical_sha256":"88eaf4bafd763e8bf770f05f978754c5c904c8c059014dd854eaad832294ffb6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:16.015147Z","signature_b64":"fb6ATNWIcdxVC4aWm/UKv/Ug5LY4KhxsDwC3OyLG2W9grGU9i60U99PQ1TgCUQzdHJq/z4q1Mu2/Sm33XTVFBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"88eaf4bafd763e8bf770f05f978754c5c904c8c059014dd854eaad832294ffb6","last_reissued_at":"2026-05-17T23:51:16.014753Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:16.014753Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1903.05844","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:51:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n5CfbK+TukXswXv9IYgfkSQQcLBnGI9LQbtkkZRimGn2r73PSmDEm/mdKSU3P04KWCCtevzvj7pqw1MQkbP+Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T17:02:32.851728Z"},"content_sha256":"5dcf3e3f6a95be96eb7b02e9bdd9aca4eede1708d22be70d1012afad2cd38796","schema_version":"1.0","event_id":"sha256:5dcf3e3f6a95be96eb7b02e9bdd9aca4eede1708d22be70d1012afad2cd38796"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:RDVPJOX5OY7IX53Q6BPZPB2UYX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Dependency Structures for Weak Supervision Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alexander Ratner, Ann He, Christopher R\\'e, Frederic Sala, Paroma Varma","submitted_at":"2019-03-14T07:55:52Z","abstract_excerpt":"Labeling training data is a key bottleneck in the modern machine learning pipeline. Recent weak supervision approaches combine labels from multiple noisy sources by estimating their accuracies without access to ground truth labels; however, estimating the dependencies among these sources is a critical challenge. We focus on a robust PCA-based algorithm for learning these dependency structures, establish improved theoretical recovery rates, and outperform existing methods on various real-world tasks. Under certain conditions, we show that the amount of unlabeled data needed can scale sublinearl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.05844","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":""},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:51:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v4UcZbq477qDZnbVuEVxa6m0xx7mtOU1yoZYNfjyczhSCKqa2YZUJQgto0l/mhV8r5Nv9iSs3vs440b068XjCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T17:02:32.852377Z"},"content_sha256":"a3a59de99db4cda1b5c1a74b025902ac6a8e23651f7aeff89508b76f7cb75334","schema_version":"1.0","event_id":"sha256:a3a59de99db4cda1b5c1a74b025902ac6a8e23651f7aeff89508b76f7cb75334"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RDVPJOX5OY7IX53Q6BPZPB2UYX/bundle.json","state_url":"https://pith.science/pith/RDVPJOX5OY7IX53Q6BPZPB2UYX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RDVPJOX5OY7IX53Q6BPZPB2UYX/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-25T17:02:32Z","links":{"resolver":"https://pith.science/pith/RDVPJOX5OY7IX53Q6BPZPB2UYX","bundle":"https://pith.science/pith/RDVPJOX5OY7IX53Q6BPZPB2UYX/bundle.json","state":"https://pith.science/pith/RDVPJOX5OY7IX53Q6BPZPB2UYX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RDVPJOX5OY7IX53Q6BPZPB2UYX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:RDVPJOX5OY7IX53Q6BPZPB2UYX","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":"5ee93d6f8cc359f670dc4be51f1b6d6813a25539d7ddf06e75a49f9864119e40","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-03-14T07:55:52Z","title_canon_sha256":"0a2284b59d8ca046144ca3b4ac36d228a27dae94cc2d59de053cd1786cce6611"},"schema_version":"1.0","source":{"id":"1903.05844","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.05844","created_at":"2026-05-17T23:51:16Z"},{"alias_kind":"arxiv_version","alias_value":"1903.05844v1","created_at":"2026-05-17T23:51:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.05844","created_at":"2026-05-17T23:51:16Z"},{"alias_kind":"pith_short_12","alias_value":"RDVPJOX5OY7I","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"RDVPJOX5OY7IX53Q","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"RDVPJOX5","created_at":"2026-05-18T12:33:27Z"}],"graph_snapshots":[{"event_id":"sha256:a3a59de99db4cda1b5c1a74b025902ac6a8e23651f7aeff89508b76f7cb75334","target":"graph","created_at":"2026-05-17T23:51:16Z","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"},"paper":{"abstract_excerpt":"Labeling training data is a key bottleneck in the modern machine learning pipeline. Recent weak supervision approaches combine labels from multiple noisy sources by estimating their accuracies without access to ground truth labels; however, estimating the dependencies among these sources is a critical challenge. We focus on a robust PCA-based algorithm for learning these dependency structures, establish improved theoretical recovery rates, and outperform existing methods on various real-world tasks. Under certain conditions, we show that the amount of unlabeled data needed can scale sublinearl","authors_text":"Alexander Ratner, Ann He, Christopher R\\'e, Frederic Sala, Paroma Varma","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-03-14T07:55:52Z","title":"Learning Dependency Structures for Weak Supervision Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.05844","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":"sha256:5dcf3e3f6a95be96eb7b02e9bdd9aca4eede1708d22be70d1012afad2cd38796","target":"record","created_at":"2026-05-17T23:51:16Z","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":"5ee93d6f8cc359f670dc4be51f1b6d6813a25539d7ddf06e75a49f9864119e40","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-03-14T07:55:52Z","title_canon_sha256":"0a2284b59d8ca046144ca3b4ac36d228a27dae94cc2d59de053cd1786cce6611"},"schema_version":"1.0","source":{"id":"1903.05844","kind":"arxiv","version":1}},"canonical_sha256":"88eaf4bafd763e8bf770f05f978754c5c904c8c059014dd854eaad832294ffb6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"88eaf4bafd763e8bf770f05f978754c5c904c8c059014dd854eaad832294ffb6","first_computed_at":"2026-05-17T23:51:16.014753Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:51:16.014753Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fb6ATNWIcdxVC4aWm/UKv/Ug5LY4KhxsDwC3OyLG2W9grGU9i60U99PQ1TgCUQzdHJq/z4q1Mu2/Sm33XTVFBA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:51:16.015147Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.05844","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5dcf3e3f6a95be96eb7b02e9bdd9aca4eede1708d22be70d1012afad2cd38796","sha256:a3a59de99db4cda1b5c1a74b025902ac6a8e23651f7aeff89508b76f7cb75334"],"state_sha256":"8d9e28b4049b51875bd9e3dcfa34e4cbd6dbdc491358fe73ea8e9e7a536da337"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Nq7vWEkjKA3SfjtjT/B4qf1GyWk2zIO0Yp1x9cDPiAwOOVpJ+KRrjxF5k6Asu7O5Dp9rcz28nY4Irdg0fer2Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T17:02:32.855930Z","bundle_sha256":"30d60cc0c7b505f4a1348d07bb4994a9d9b188f9fc072f77fcb591aaeded87c9"}}