{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:7YEBTLVL3CVPPNZBHNC46V25PF","short_pith_number":"pith:7YEBTLVL","schema_version":"1.0","canonical_sha256":"fe0819aeabd8aaf7b7213b45cf575d7963661cd8907d3b74e41a2e0b8c228094","source":{"kind":"arxiv","id":"1711.11383","version":1},"attestation_state":"computed","paper":{"title":"Learning to Learn from Weak Supervision by Full Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"stat.ML","authors_text":"Aliaksei Severyn, Jaap Kamps, Mostafa Dehghani, Sascha Rothe","submitted_at":"2017-11-30T13:32:45Z","abstract_excerpt":"In this paper, we propose a method for training neural networks when we have a large set of data with weak labels and a small amount of data with true labels. In our proposed model, we train two neural networks: a target network, the learner and a confidence network, the meta-learner. The target network is optimized to perform a given task and is trained using a large set of unlabeled data that are weakly annotated. We propose to control the magnitude of the gradient updates to the target network using the scores provided by the second confidence network, which is trained on a small amount of "},"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":"1711.11383","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-11-30T13:32:45Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"94d1d5d45e5268a5b03459956effd74c742687e9aee88b28abf711847381eff7","abstract_canon_sha256":"551d2bc9ae080d6846445be0191ed72408fbb86f6c44182ec358d76162dd481a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:29:11.747370Z","signature_b64":"8buvKiQGMmcQJtMtzVZgI1tQle/wUqI3sJXNWhytFlcQiI7TfelOtNicWg+VvdxNIMrSLl2UfKnwXGaSeABZBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe0819aeabd8aaf7b7213b45cf575d7963661cd8907d3b74e41a2e0b8c228094","last_reissued_at":"2026-05-18T00:29:11.746715Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:29:11.746715Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Learn from Weak Supervision by Full Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"stat.ML","authors_text":"Aliaksei Severyn, Jaap Kamps, Mostafa Dehghani, Sascha Rothe","submitted_at":"2017-11-30T13:32:45Z","abstract_excerpt":"In this paper, we propose a method for training neural networks when we have a large set of data with weak labels and a small amount of data with true labels. In our proposed model, we train two neural networks: a target network, the learner and a confidence network, the meta-learner. The target network is optimized to perform a given task and is trained using a large set of unlabeled data that are weakly annotated. We propose to control the magnitude of the gradient updates to the target network using the scores provided by the second confidence network, which is trained on a small amount of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.11383","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":""},"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":"1711.11383","created_at":"2026-05-18T00:29:11.746811+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.11383v1","created_at":"2026-05-18T00:29:11.746811+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.11383","created_at":"2026-05-18T00:29:11.746811+00:00"},{"alias_kind":"pith_short_12","alias_value":"7YEBTLVL3CVP","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_16","alias_value":"7YEBTLVL3CVPPNZB","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_8","alias_value":"7YEBTLVL","created_at":"2026-05-18T12:31:05.417338+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7YEBTLVL3CVPPNZBHNC46V25PF","json":"https://pith.science/pith/7YEBTLVL3CVPPNZBHNC46V25PF.json","graph_json":"https://pith.science/api/pith-number/7YEBTLVL3CVPPNZBHNC46V25PF/graph.json","events_json":"https://pith.science/api/pith-number/7YEBTLVL3CVPPNZBHNC46V25PF/events.json","paper":"https://pith.science/paper/7YEBTLVL"},"agent_actions":{"view_html":"https://pith.science/pith/7YEBTLVL3CVPPNZBHNC46V25PF","download_json":"https://pith.science/pith/7YEBTLVL3CVPPNZBHNC46V25PF.json","view_paper":"https://pith.science/paper/7YEBTLVL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.11383&json=true","fetch_graph":"https://pith.science/api/pith-number/7YEBTLVL3CVPPNZBHNC46V25PF/graph.json","fetch_events":"https://pith.science/api/pith-number/7YEBTLVL3CVPPNZBHNC46V25PF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7YEBTLVL3CVPPNZBHNC46V25PF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7YEBTLVL3CVPPNZBHNC46V25PF/action/storage_attestation","attest_author":"https://pith.science/pith/7YEBTLVL3CVPPNZBHNC46V25PF/action/author_attestation","sign_citation":"https://pith.science/pith/7YEBTLVL3CVPPNZBHNC46V25PF/action/citation_signature","submit_replication":"https://pith.science/pith/7YEBTLVL3CVPPNZBHNC46V25PF/action/replication_record"}},"created_at":"2026-05-18T00:29:11.746811+00:00","updated_at":"2026-05-18T00:29:11.746811+00:00"}