{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:4I3HQTR437OSSI3SMSAYBQYQCF","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":"5a64313a04ced61a2cdda086195bca45fb0da678af64b11ad1ab1e8341a2bcbd","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2020-05-13T03:29:12Z","title_canon_sha256":"d94ec80a08856dce68765c055ff8708894100d12de84c15656667ebc69fec776"},"schema_version":"1.0","source":{"id":"2005.06133","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.06133","created_at":"2026-07-05T01:02:32Z"},{"alias_kind":"arxiv_version","alias_value":"2005.06133v1","created_at":"2026-07-05T01:02:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.06133","created_at":"2026-07-05T01:02:32Z"},{"alias_kind":"pith_short_12","alias_value":"4I3HQTR437OS","created_at":"2026-07-05T01:02:32Z"},{"alias_kind":"pith_short_16","alias_value":"4I3HQTR437OSSI3S","created_at":"2026-07-05T01:02:32Z"},{"alias_kind":"pith_short_8","alias_value":"4I3HQTR4","created_at":"2026-07-05T01:02:32Z"}],"graph_snapshots":[{"event_id":"sha256:3a2529fedcbfe5d524460599042e53173da2fd876f46daff4b1f4a489cc330fc","target":"graph","created_at":"2026-07-05T01:02:32Z","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/2005.06133/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Creating and collecting labeled data is one of the major bottlenecks in machine learning pipelines and the emergence of automated feature generation techniques such as deep learning, which typically requires a lot of training data, has further exacerbated the problem. While weak-supervision techniques have circumvented this bottleneck, existing frameworks either require users to write a set of diverse, high-quality rules to label data (e.g., Snorkel), or require a labeled subset of the data to automatically mine rules (e.g., Snuba). The process of manually writing rules can be tedious and time","authors_text":"Behzad Golshan, Sainyam Galhotra, Wang-Chiew Tan","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2020-05-13T03:29:12Z","title":"Adaptive Rule Discovery for Labeling Text Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.06133","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:d134c7fd7643cea9be7cdcb26ab468f4a8c4c96687c7164d577c0c67199beec1","target":"record","created_at":"2026-07-05T01:02:32Z","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":"5a64313a04ced61a2cdda086195bca45fb0da678af64b11ad1ab1e8341a2bcbd","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2020-05-13T03:29:12Z","title_canon_sha256":"d94ec80a08856dce68765c055ff8708894100d12de84c15656667ebc69fec776"},"schema_version":"1.0","source":{"id":"2005.06133","kind":"arxiv","version":1}},"canonical_sha256":"e236784e3cdfdd292372648180c3101162ee6e35cc03fc52897cb7daca27868b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e236784e3cdfdd292372648180c3101162ee6e35cc03fc52897cb7daca27868b","first_computed_at":"2026-07-05T01:02:32.346213Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:02:32.346213Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nTK/iCl+1Y4zC9FunpO2xTDp9DwTKiGs4Q0PJSIa73DZNlLqZm89yS1KtmuaNgGwKrrGir3APVscBQbxBefBDA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:02:32.346646Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.06133","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d134c7fd7643cea9be7cdcb26ab468f4a8c4c96687c7164d577c0c67199beec1","sha256:3a2529fedcbfe5d524460599042e53173da2fd876f46daff4b1f4a489cc330fc"],"state_sha256":"b5028005a3073f4b06cc819697cbd0fae4af3ddd9f147be82356728a9f9cac68"}