{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:XOB363VJCKMX32IEEFG67JDLWW","short_pith_number":"pith:XOB363VJ","canonical_record":{"source":{"id":"1812.00417","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-02T16:23:36Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4c3d08b9972edf8d9e931e77a149b04a1b9ec35e70df9eb5d0230a3e6f4399ab","abstract_canon_sha256":"23bba33a64b27180f307722ee2926054bf51826b645cb4ba4e2693429bcf8a1c"},"schema_version":"1.0"},"canonical_sha256":"bb83bf6ea912997de904214defa46bb5ba94afd356098bf5b34adbb976deb18a","source":{"kind":"arxiv","id":"1812.00417","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.00417","created_at":"2026-05-17T23:44:22Z"},{"alias_kind":"arxiv_version","alias_value":"1812.00417v2","created_at":"2026-05-17T23:44:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.00417","created_at":"2026-05-17T23:44:22Z"},{"alias_kind":"pith_short_12","alias_value":"XOB363VJCKMX","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"XOB363VJCKMX32IE","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"XOB363VJ","created_at":"2026-05-18T12:33:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:XOB363VJCKMX32IEEFG67JDLWW","target":"record","payload":{"canonical_record":{"source":{"id":"1812.00417","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-02T16:23:36Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4c3d08b9972edf8d9e931e77a149b04a1b9ec35e70df9eb5d0230a3e6f4399ab","abstract_canon_sha256":"23bba33a64b27180f307722ee2926054bf51826b645cb4ba4e2693429bcf8a1c"},"schema_version":"1.0"},"canonical_sha256":"bb83bf6ea912997de904214defa46bb5ba94afd356098bf5b34adbb976deb18a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:22.089166Z","signature_b64":"jauJfuADgjSx93VhokLW7kb/QOf0OpAX/5mNpyVzxJ9P+PKMeHi5s1fautAr/4M8THwINJw5vMYCvyKMqnCpDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb83bf6ea912997de904214defa46bb5ba94afd356098bf5b34adbb976deb18a","last_reissued_at":"2026-05-17T23:44:22.088529Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:22.088529Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1812.00417","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:44:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XJMWpBQhBD3cLhoT/be8fBhJFjbBAV/uKWxDh3tvwG8R3oY0y5VTUl5Ck0yr0fyWH1BNpKu9o7VlUy1FQ3zLAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T19:54:52.930364Z"},"content_sha256":"ad652c91ee4702b934055541d6c9a39c1a2075774adbe2df42ba8af71f12a10e","schema_version":"1.0","event_id":"sha256:ad652c91ee4702b934055541d6c9a39c1a2075774adbe2df42ba8af71f12a10e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:XOB363VJCKMX32IEEFG67JDLWW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Snorkel DryBell: A Case Study in Deploying Weak Supervision at Industrial Scale","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Ratner, Braden Hancock, Cassandra Xia, Chong Luo, Christopher R\\'e, Daniel Rodriguez, Haidong Shao, Houman Alborzi, Rahul Kuchhal, Rob Malkin, Souvik Sen, Stephen H. Bach, Yintao Liu","submitted_at":"2018-12-02T16:23:36Z","abstract_excerpt":"Labeling training data is one of the most costly bottlenecks in developing machine learning-based applications. We present a first-of-its-kind study showing how existing knowledge resources from across an organization can be used as weak supervision in order to bring development time and cost down by an order of magnitude, and introduce Snorkel DryBell, a new weak supervision management system for this setting. Snorkel DryBell builds on the Snorkel framework, extending it in three critical aspects: flexible, template-based ingestion of diverse organizational knowledge, cross-feature production"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.00417","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":""},"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":"2026-05-17T23:44:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ycXgIUMlK/zxhEH7XFSqwynExew8tBHVKheKZuI0FWUHfm7MYXQeT0n0CGhP2MIMl62hjZdGPDYLywSrPUoGBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T19:54:52.931102Z"},"content_sha256":"7c9631c0c1da04363f4ac5687726f7d54b3aeef87e1d361f820f602d990deba9","schema_version":"1.0","event_id":"sha256:7c9631c0c1da04363f4ac5687726f7d54b3aeef87e1d361f820f602d990deba9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XOB363VJCKMX32IEEFG67JDLWW/bundle.json","state_url":"https://pith.science/pith/XOB363VJCKMX32IEEFG67JDLWW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XOB363VJCKMX32IEEFG67JDLWW/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":"2026-06-06T19:54:52Z","links":{"resolver":"https://pith.science/pith/XOB363VJCKMX32IEEFG67JDLWW","bundle":"https://pith.science/pith/XOB363VJCKMX32IEEFG67JDLWW/bundle.json","state":"https://pith.science/pith/XOB363VJCKMX32IEEFG67JDLWW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XOB363VJCKMX32IEEFG67JDLWW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:XOB363VJCKMX32IEEFG67JDLWW","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":"23bba33a64b27180f307722ee2926054bf51826b645cb4ba4e2693429bcf8a1c","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-02T16:23:36Z","title_canon_sha256":"4c3d08b9972edf8d9e931e77a149b04a1b9ec35e70df9eb5d0230a3e6f4399ab"},"schema_version":"1.0","source":{"id":"1812.00417","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.00417","created_at":"2026-05-17T23:44:22Z"},{"alias_kind":"arxiv_version","alias_value":"1812.00417v2","created_at":"2026-05-17T23:44:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.00417","created_at":"2026-05-17T23:44:22Z"},{"alias_kind":"pith_short_12","alias_value":"XOB363VJCKMX","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"XOB363VJCKMX32IE","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"XOB363VJ","created_at":"2026-05-18T12:33:01Z"}],"graph_snapshots":[{"event_id":"sha256:7c9631c0c1da04363f4ac5687726f7d54b3aeef87e1d361f820f602d990deba9","target":"graph","created_at":"2026-05-17T23:44:22Z","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 one of the most costly bottlenecks in developing machine learning-based applications. We present a first-of-its-kind study showing how existing knowledge resources from across an organization can be used as weak supervision in order to bring development time and cost down by an order of magnitude, and introduce Snorkel DryBell, a new weak supervision management system for this setting. Snorkel DryBell builds on the Snorkel framework, extending it in three critical aspects: flexible, template-based ingestion of diverse organizational knowledge, cross-feature production","authors_text":"Alexander Ratner, Braden Hancock, Cassandra Xia, Chong Luo, Christopher R\\'e, Daniel Rodriguez, Haidong Shao, Houman Alborzi, Rahul Kuchhal, Rob Malkin, Souvik Sen, Stephen H. Bach, Yintao Liu","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-02T16:23:36Z","title":"Snorkel DryBell: A Case Study in Deploying Weak Supervision at Industrial Scale"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.00417","kind":"arxiv","version":2},"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:ad652c91ee4702b934055541d6c9a39c1a2075774adbe2df42ba8af71f12a10e","target":"record","created_at":"2026-05-17T23:44:22Z","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":"23bba33a64b27180f307722ee2926054bf51826b645cb4ba4e2693429bcf8a1c","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-02T16:23:36Z","title_canon_sha256":"4c3d08b9972edf8d9e931e77a149b04a1b9ec35e70df9eb5d0230a3e6f4399ab"},"schema_version":"1.0","source":{"id":"1812.00417","kind":"arxiv","version":2}},"canonical_sha256":"bb83bf6ea912997de904214defa46bb5ba94afd356098bf5b34adbb976deb18a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bb83bf6ea912997de904214defa46bb5ba94afd356098bf5b34adbb976deb18a","first_computed_at":"2026-05-17T23:44:22.088529Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:44:22.088529Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jauJfuADgjSx93VhokLW7kb/QOf0OpAX/5mNpyVzxJ9P+PKMeHi5s1fautAr/4M8THwINJw5vMYCvyKMqnCpDw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:44:22.089166Z","signed_message":"canonical_sha256_bytes"},"source_id":"1812.00417","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ad652c91ee4702b934055541d6c9a39c1a2075774adbe2df42ba8af71f12a10e","sha256:7c9631c0c1da04363f4ac5687726f7d54b3aeef87e1d361f820f602d990deba9"],"state_sha256":"a69ab154cd08ffae4f4a42724e3ce0af17ac8898cc68d86cc999eda114a7fcb9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fYCHBBT3MdlCCyin0iUdG14MFd7kAeo81CXtfxwKbXfHV08vao4d8QSJl09FL4OvYbkaxEqA90idlvjGq4XGBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T19:54:52.934740Z","bundle_sha256":"9c669356a25aee9f74ede6bcc307f951f374c05ab3777f9959ed5b0c6a56c30b"}}