{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WVAUXMX2R4XGOXHETWA3K6QNL3","short_pith_number":"pith:WVAUXMX2","schema_version":"1.0","canonical_sha256":"b5414bb2fa8f2e675ce49d81b57a0d5ed8d69724192880b53be9e8550ae3e54d","source":{"kind":"arxiv","id":"2508.03896","version":1},"attestation_state":"computed","paper":{"title":"Reliable Programmatic Weak Supervision with Confidence Intervals for Label Probabilities","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Sanjoy Dasgupta, Santiago Mazuelas, Steven An, Ver\\'onica \\'Alvarez","submitted_at":"2025-08-05T20:34:04Z","abstract_excerpt":"The accurate labeling of datasets is often both costly and time-consuming. Given an unlabeled dataset, programmatic weak supervision obtains probabilistic predictions for the labels by leveraging multiple weak labeling functions (LFs) that provide rough guesses for labels. Weak LFs commonly provide guesses with assorted types and unknown interdependences that can result in unreliable predictions. Furthermore, existing techniques for programmatic weak supervision cannot provide assessments for the reliability of the probabilistic predictions for labels. This paper presents a methodology for pro"},"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":"2508.03896","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-08-05T20:34:04Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2558640b6cf64fff1a17c17698b241b8ffea426238a9466533789f896b97fce5","abstract_canon_sha256":"c4b21501b8643f43f33da3acd132e43608dfd7af3a46a28b9a897b50c7b3d3ca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:16.835948Z","signature_b64":"lWJLMSFJ5L4DNDT9S8KlazXtCRLOO8dGr3YTywD58eIdoAYItqkA0K/UWCe7xY0mv6eLeD6SN3dBLpH1vgLfCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b5414bb2fa8f2e675ce49d81b57a0d5ed8d69724192880b53be9e8550ae3e54d","last_reissued_at":"2026-07-05T11:49:16.835441Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:16.835441Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reliable Programmatic Weak Supervision with Confidence Intervals for Label Probabilities","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Sanjoy Dasgupta, Santiago Mazuelas, Steven An, Ver\\'onica \\'Alvarez","submitted_at":"2025-08-05T20:34:04Z","abstract_excerpt":"The accurate labeling of datasets is often both costly and time-consuming. Given an unlabeled dataset, programmatic weak supervision obtains probabilistic predictions for the labels by leveraging multiple weak labeling functions (LFs) that provide rough guesses for labels. Weak LFs commonly provide guesses with assorted types and unknown interdependences that can result in unreliable predictions. Furthermore, existing techniques for programmatic weak supervision cannot provide assessments for the reliability of the probabilistic predictions for labels. This paper presents a methodology for pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.03896","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2508.03896/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":"2508.03896","created_at":"2026-07-05T11:49:16.835498+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.03896v1","created_at":"2026-07-05T11:49:16.835498+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.03896","created_at":"2026-07-05T11:49:16.835498+00:00"},{"alias_kind":"pith_short_12","alias_value":"WVAUXMX2R4XG","created_at":"2026-07-05T11:49:16.835498+00:00"},{"alias_kind":"pith_short_16","alias_value":"WVAUXMX2R4XGOXHE","created_at":"2026-07-05T11:49:16.835498+00:00"},{"alias_kind":"pith_short_8","alias_value":"WVAUXMX2","created_at":"2026-07-05T11:49:16.835498+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.03897","citing_title":"A note on real Heegaard Floer homology and localization","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WVAUXMX2R4XGOXHETWA3K6QNL3","json":"https://pith.science/pith/WVAUXMX2R4XGOXHETWA3K6QNL3.json","graph_json":"https://pith.science/api/pith-number/WVAUXMX2R4XGOXHETWA3K6QNL3/graph.json","events_json":"https://pith.science/api/pith-number/WVAUXMX2R4XGOXHETWA3K6QNL3/events.json","paper":"https://pith.science/paper/WVAUXMX2"},"agent_actions":{"view_html":"https://pith.science/pith/WVAUXMX2R4XGOXHETWA3K6QNL3","download_json":"https://pith.science/pith/WVAUXMX2R4XGOXHETWA3K6QNL3.json","view_paper":"https://pith.science/paper/WVAUXMX2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.03896&json=true","fetch_graph":"https://pith.science/api/pith-number/WVAUXMX2R4XGOXHETWA3K6QNL3/graph.json","fetch_events":"https://pith.science/api/pith-number/WVAUXMX2R4XGOXHETWA3K6QNL3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WVAUXMX2R4XGOXHETWA3K6QNL3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WVAUXMX2R4XGOXHETWA3K6QNL3/action/storage_attestation","attest_author":"https://pith.science/pith/WVAUXMX2R4XGOXHETWA3K6QNL3/action/author_attestation","sign_citation":"https://pith.science/pith/WVAUXMX2R4XGOXHETWA3K6QNL3/action/citation_signature","submit_replication":"https://pith.science/pith/WVAUXMX2R4XGOXHETWA3K6QNL3/action/replication_record"}},"created_at":"2026-07-05T11:49:16.835498+00:00","updated_at":"2026-07-05T11:49:16.835498+00:00"}