{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:A557CSIOFG36Y6FLIYDWTFF4WC","short_pith_number":"pith:A557CSIO","canonical_record":{"source":{"id":"2008.09887","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-22T17:53:16Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"295b458f0abfaeb5f8dca1a117b88444106382ef6bc74731c4cd9741ac98eb0b","abstract_canon_sha256":"a7b40a1eb0aa2a211e0ae9960a9e045594510d6d94b233049281987e5f942b76"},"schema_version":"1.0"},"canonical_sha256":"077bf1490e29b7ec78ab46076994bcb0a35cdc63a02e5337feec01be6774c9e0","source":{"kind":"arxiv","id":"2008.09887","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.09887","created_at":"2026-07-05T02:48:33Z"},{"alias_kind":"arxiv_version","alias_value":"2008.09887v3","created_at":"2026-07-05T02:48:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.09887","created_at":"2026-07-05T02:48:33Z"},{"alias_kind":"pith_short_12","alias_value":"A557CSIOFG36","created_at":"2026-07-05T02:48:33Z"},{"alias_kind":"pith_short_16","alias_value":"A557CSIOFG36Y6FL","created_at":"2026-07-05T02:48:33Z"},{"alias_kind":"pith_short_8","alias_value":"A557CSIO","created_at":"2026-07-05T02:48:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:A557CSIOFG36Y6FLIYDWTFF4WC","target":"record","payload":{"canonical_record":{"source":{"id":"2008.09887","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-22T17:53:16Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"295b458f0abfaeb5f8dca1a117b88444106382ef6bc74731c4cd9741ac98eb0b","abstract_canon_sha256":"a7b40a1eb0aa2a211e0ae9960a9e045594510d6d94b233049281987e5f942b76"},"schema_version":"1.0"},"canonical_sha256":"077bf1490e29b7ec78ab46076994bcb0a35cdc63a02e5337feec01be6774c9e0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:48:33.788140Z","signature_b64":"gm35RsZUiUnVJ05qVpVYDEhzS9impZQEQeBm4kZErDRVIjj404SIWGGrRddbyckIxWCLhnx7kQYOSXFypFLYDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"077bf1490e29b7ec78ab46076994bcb0a35cdc63a02e5337feec01be6774c9e0","last_reissued_at":"2026-07-05T02:48:33.787592Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:48:33.787592Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2008.09887","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:48:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TrFHcw82hxQVaGRDU7zxPUvcPxxdS+OvFdcAMgafxn7/BSJNScq4+wXermEzJhg/Gmvh3b5vaC7Hvro12td6AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T21:48:22.979729Z"},"content_sha256":"bf0fa79bb55f7fa77a3f658f76b70168a7809e1b2e954e4b03f97eb396d8394d","schema_version":"1.0","event_id":"sha256:bf0fa79bb55f7fa77a3f658f76b70168a7809e1b2e954e4b03f97eb396d8394d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:A557CSIOFG36Y6FLIYDWTFF4WC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Semi-Supervised Data Programming with Subset Selection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ayush Maheshwari, Ganesh Ramakrishnan, Krishnateja Killamsetty, Oishik Chatterjee, Rishabh Iyer","submitted_at":"2020-08-22T17:53:16Z","abstract_excerpt":"The paradigm of data programming, which uses weak supervision in the form of rules/labelling functions, and semi-supervised learning, which augments small amounts of labelled data with a large unlabelled dataset, have shown great promise in several text classification scenarios. In this work, we argue that by not using any labelled data, data programming based approaches can yield sub-optimal performances, particularly when the labelling functions are noisy. The first contribution of this work is an introduction of a framework, \\model which is a semi-supervised data programming paradigm that l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.09887","kind":"arxiv","version":3},"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/2008.09887/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:48:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z/Ud79gEGIFYuhiEtAGX8iZaQj/IzKQcdQIPglJRErJ0drO5oykxTfNcibRRbOuFO/mx5X65cwXywhJMsulpBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T21:48:22.980608Z"},"content_sha256":"1ae4f9a4b7b50523147fe4b362902e433a09895867b2063b422c9ab1e819ffea","schema_version":"1.0","event_id":"sha256:1ae4f9a4b7b50523147fe4b362902e433a09895867b2063b422c9ab1e819ffea"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A557CSIOFG36Y6FLIYDWTFF4WC/bundle.json","state_url":"https://pith.science/pith/A557CSIOFG36Y6FLIYDWTFF4WC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A557CSIOFG36Y6FLIYDWTFF4WC/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":"2026-08-06T21:48:22Z","links":{"resolver":"https://pith.science/pith/A557CSIOFG36Y6FLIYDWTFF4WC","bundle":"https://pith.science/pith/A557CSIOFG36Y6FLIYDWTFF4WC/bundle.json","state":"https://pith.science/pith/A557CSIOFG36Y6FLIYDWTFF4WC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A557CSIOFG36Y6FLIYDWTFF4WC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:A557CSIOFG36Y6FLIYDWTFF4WC","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":"a7b40a1eb0aa2a211e0ae9960a9e045594510d6d94b233049281987e5f942b76","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-22T17:53:16Z","title_canon_sha256":"295b458f0abfaeb5f8dca1a117b88444106382ef6bc74731c4cd9741ac98eb0b"},"schema_version":"1.0","source":{"id":"2008.09887","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.09887","created_at":"2026-07-05T02:48:33Z"},{"alias_kind":"arxiv_version","alias_value":"2008.09887v3","created_at":"2026-07-05T02:48:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.09887","created_at":"2026-07-05T02:48:33Z"},{"alias_kind":"pith_short_12","alias_value":"A557CSIOFG36","created_at":"2026-07-05T02:48:33Z"},{"alias_kind":"pith_short_16","alias_value":"A557CSIOFG36Y6FL","created_at":"2026-07-05T02:48:33Z"},{"alias_kind":"pith_short_8","alias_value":"A557CSIO","created_at":"2026-07-05T02:48:33Z"}],"graph_snapshots":[{"event_id":"sha256:1ae4f9a4b7b50523147fe4b362902e433a09895867b2063b422c9ab1e819ffea","target":"graph","created_at":"2026-07-05T02:48:33Z","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/2008.09887/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The paradigm of data programming, which uses weak supervision in the form of rules/labelling functions, and semi-supervised learning, which augments small amounts of labelled data with a large unlabelled dataset, have shown great promise in several text classification scenarios. In this work, we argue that by not using any labelled data, data programming based approaches can yield sub-optimal performances, particularly when the labelling functions are noisy. The first contribution of this work is an introduction of a framework, \\model which is a semi-supervised data programming paradigm that l","authors_text":"Ayush Maheshwari, Ganesh Ramakrishnan, Krishnateja Killamsetty, Oishik Chatterjee, Rishabh Iyer","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-22T17:53:16Z","title":"Semi-Supervised Data Programming with Subset Selection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.09887","kind":"arxiv","version":3},"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:bf0fa79bb55f7fa77a3f658f76b70168a7809e1b2e954e4b03f97eb396d8394d","target":"record","created_at":"2026-07-05T02:48:33Z","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":"a7b40a1eb0aa2a211e0ae9960a9e045594510d6d94b233049281987e5f942b76","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-22T17:53:16Z","title_canon_sha256":"295b458f0abfaeb5f8dca1a117b88444106382ef6bc74731c4cd9741ac98eb0b"},"schema_version":"1.0","source":{"id":"2008.09887","kind":"arxiv","version":3}},"canonical_sha256":"077bf1490e29b7ec78ab46076994bcb0a35cdc63a02e5337feec01be6774c9e0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"077bf1490e29b7ec78ab46076994bcb0a35cdc63a02e5337feec01be6774c9e0","first_computed_at":"2026-07-05T02:48:33.787592Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:48:33.787592Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gm35RsZUiUnVJ05qVpVYDEhzS9impZQEQeBm4kZErDRVIjj404SIWGGrRddbyckIxWCLhnx7kQYOSXFypFLYDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:48:33.788140Z","signed_message":"canonical_sha256_bytes"},"source_id":"2008.09887","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bf0fa79bb55f7fa77a3f658f76b70168a7809e1b2e954e4b03f97eb396d8394d","sha256:1ae4f9a4b7b50523147fe4b362902e433a09895867b2063b422c9ab1e819ffea"],"state_sha256":"93f29baedf060ec9ac32a36407b2c4c4c73e16d01e65b440e1abc7a40b9615f3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IleVOScq2+FMdFvzJnyvDLfehbR5u/uwTgNbAo9zZs9jcnfbQ8nsotx2psQFZgYn0xO10o6wTmwBSTxqyJAsCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T21:48:22.987688Z","bundle_sha256":"a3568f5f8d83c871a2c3e2955d2a5573d28dfee72c07f71b04096c532cff36e9"}}