{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:WOJCZCFETLL5UV54P4WJTV7JKZ","short_pith_number":"pith:WOJCZCFE","schema_version":"1.0","canonical_sha256":"b3922c88a49ad7da57bc7f2c99d7e9564c822ded12e43590be4f2770fefd8590","source":{"kind":"arxiv","id":"2109.11377","version":2},"attestation_state":"computed","paper":{"title":"WRENCH: A Comprehensive Benchmark for Weak Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Ratner, Jieyu Zhang, Mao Yang, Yaming Yang, Yinghao Li, Yue Yu, Yujing Wang","submitted_at":"2021-09-23T13:47:16Z","abstract_excerpt":"Recent Weak Supervision (WS) approaches have had widespread success in easing the bottleneck of labeling training data for machine learning by synthesizing labels from multiple potentially noisy supervision sources. However, proper measurement and analysis of these approaches remain a challenge. First, datasets used in existing works are often private and/or custom, limiting standardization. Second, WS datasets with the same name and base data often vary in terms of the labels and weak supervision sources used, a significant \"hidden\" source of evaluation variance. Finally, WS studies often div"},"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":"2109.11377","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-23T13:47:16Z","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"title_canon_sha256":"0a1b7d8757c271efac924077708f7dd460de149e4277b42528e4b2f7b68d5bc5","abstract_canon_sha256":"c0420093d96ad2985858d821b478a6fbd4ff17cf7d9a6061026934c2cfb11c5f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:21:14.205424Z","signature_b64":"Ie8ObM5ZJI5Kz9eervOgHWfSHA9Mg7ayluJP3vrnTzsrJjbX5Xf+TOpM5OrCYFqAFf/IwSWNedE4Y1Aig+XTDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b3922c88a49ad7da57bc7f2c99d7e9564c822ded12e43590be4f2770fefd8590","last_reissued_at":"2026-07-05T03:21:14.204999Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:21:14.204999Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WRENCH: A Comprehensive Benchmark for Weak Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Ratner, Jieyu Zhang, Mao Yang, Yaming Yang, Yinghao Li, Yue Yu, Yujing Wang","submitted_at":"2021-09-23T13:47:16Z","abstract_excerpt":"Recent Weak Supervision (WS) approaches have had widespread success in easing the bottleneck of labeling training data for machine learning by synthesizing labels from multiple potentially noisy supervision sources. However, proper measurement and analysis of these approaches remain a challenge. First, datasets used in existing works are often private and/or custom, limiting standardization. Second, WS datasets with the same name and base data often vary in terms of the labels and weak supervision sources used, a significant \"hidden\" source of evaluation variance. Finally, WS studies often div"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.11377","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2109.11377/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":"2109.11377","created_at":"2026-07-05T03:21:14.205056+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.11377v2","created_at":"2026-07-05T03:21:14.205056+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.11377","created_at":"2026-07-05T03:21:14.205056+00:00"},{"alias_kind":"pith_short_12","alias_value":"WOJCZCFETLL5","created_at":"2026-07-05T03:21:14.205056+00:00"},{"alias_kind":"pith_short_16","alias_value":"WOJCZCFETLL5UV54","created_at":"2026-07-05T03:21:14.205056+00:00"},{"alias_kind":"pith_short_8","alias_value":"WOJCZCFE","created_at":"2026-07-05T03:21:14.205056+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.18036","citing_title":"Harnessing Multiple Large Language Models: A Survey on LLM Ensemble","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2512.23213","citing_title":"Scoring, Reasoning, and Selecting the Best! Ensembling Large Language Models via a Peer-Review Process","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03158","citing_title":"HackerSignal: A Large-Scale Multi-Source Dataset Linking Hacker Community Discourse to the CVE Vulnerability Lifecycle","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WOJCZCFETLL5UV54P4WJTV7JKZ","json":"https://pith.science/pith/WOJCZCFETLL5UV54P4WJTV7JKZ.json","graph_json":"https://pith.science/api/pith-number/WOJCZCFETLL5UV54P4WJTV7JKZ/graph.json","events_json":"https://pith.science/api/pith-number/WOJCZCFETLL5UV54P4WJTV7JKZ/events.json","paper":"https://pith.science/paper/WOJCZCFE"},"agent_actions":{"view_html":"https://pith.science/pith/WOJCZCFETLL5UV54P4WJTV7JKZ","download_json":"https://pith.science/pith/WOJCZCFETLL5UV54P4WJTV7JKZ.json","view_paper":"https://pith.science/paper/WOJCZCFE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.11377&json=true","fetch_graph":"https://pith.science/api/pith-number/WOJCZCFETLL5UV54P4WJTV7JKZ/graph.json","fetch_events":"https://pith.science/api/pith-number/WOJCZCFETLL5UV54P4WJTV7JKZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WOJCZCFETLL5UV54P4WJTV7JKZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WOJCZCFETLL5UV54P4WJTV7JKZ/action/storage_attestation","attest_author":"https://pith.science/pith/WOJCZCFETLL5UV54P4WJTV7JKZ/action/author_attestation","sign_citation":"https://pith.science/pith/WOJCZCFETLL5UV54P4WJTV7JKZ/action/citation_signature","submit_replication":"https://pith.science/pith/WOJCZCFETLL5UV54P4WJTV7JKZ/action/replication_record"}},"created_at":"2026-07-05T03:21:14.205056+00:00","updated_at":"2026-07-05T03:21:14.205056+00:00"}