{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:DWJFRI6HNPZX2FPMWNWYQ6JNVV","short_pith_number":"pith:DWJFRI6H","schema_version":"1.0","canonical_sha256":"1d9258a3c76bf37d15ecb36d88792dad57b4725329906f58eacb524402c3c8bb","source":{"kind":"arxiv","id":"1905.11658","version":3},"attestation_state":"computed","paper":{"title":"DSReg: Using Distant Supervision as a Regularizer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiwei Li, Muyu Li, Wei Wu, Xiaoya Li, Yuxian Meng","submitted_at":"2019-05-28T07:46:50Z","abstract_excerpt":"In this paper, we aim at tackling a general issue in NLP tasks where some of the negative examples are highly similar to the positive examples, i.e., hard-negative examples. We propose the distant supervision as a regularizer (DSReg) approach to tackle this issue. The original task is converted to a multi-task learning problem, in which distant supervision is used to retrieve hard-negative examples. The obtained hard-negative examples are then used as a regularizer. The original target objective of distinguishing positive examples from negative examples is jointly optimized with the auxiliary "},"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":"1905.11658","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-28T07:46:50Z","cross_cats_sorted":[],"title_canon_sha256":"b3bb9e8143323cc102cd63d38309915be8c54d1dc10d06a0a20324ebf1073da1","abstract_canon_sha256":"af0b19d58e1b8f27b88cfafa973f57f172b6c8613dc6c26f5b9ba72c0b95469d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:07:23.509822Z","signature_b64":"pFqY7WUa8/2gYnHpZEwFgSDqHOsMoYkhzVv4zp9pZMkf3S44hhk9mB4nOjBJfwbvLTfD2o/Y88Lz+nXBIOUHAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d9258a3c76bf37d15ecb36d88792dad57b4725329906f58eacb524402c3c8bb","last_reissued_at":"2026-07-05T00:07:23.509351Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:07:23.509351Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DSReg: Using Distant Supervision as a Regularizer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiwei Li, Muyu Li, Wei Wu, Xiaoya Li, Yuxian Meng","submitted_at":"2019-05-28T07:46:50Z","abstract_excerpt":"In this paper, we aim at tackling a general issue in NLP tasks where some of the negative examples are highly similar to the positive examples, i.e., hard-negative examples. We propose the distant supervision as a regularizer (DSReg) approach to tackle this issue. The original task is converted to a multi-task learning problem, in which distant supervision is used to retrieve hard-negative examples. The obtained hard-negative examples are then used as a regularizer. The original target objective of distinguishing positive examples from negative examples is jointly optimized with the auxiliary "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.11658","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/1905.11658/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":"1905.11658","created_at":"2026-07-05T00:07:23.509407+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.11658v3","created_at":"2026-07-05T00:07:23.509407+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.11658","created_at":"2026-07-05T00:07:23.509407+00:00"},{"alias_kind":"pith_short_12","alias_value":"DWJFRI6HNPZX","created_at":"2026-07-05T00:07:23.509407+00:00"},{"alias_kind":"pith_short_16","alias_value":"DWJFRI6HNPZX2FPM","created_at":"2026-07-05T00:07:23.509407+00:00"},{"alias_kind":"pith_short_8","alias_value":"DWJFRI6H","created_at":"2026-07-05T00:07:23.509407+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/DWJFRI6HNPZX2FPMWNWYQ6JNVV","json":"https://pith.science/pith/DWJFRI6HNPZX2FPMWNWYQ6JNVV.json","graph_json":"https://pith.science/api/pith-number/DWJFRI6HNPZX2FPMWNWYQ6JNVV/graph.json","events_json":"https://pith.science/api/pith-number/DWJFRI6HNPZX2FPMWNWYQ6JNVV/events.json","paper":"https://pith.science/paper/DWJFRI6H"},"agent_actions":{"view_html":"https://pith.science/pith/DWJFRI6HNPZX2FPMWNWYQ6JNVV","download_json":"https://pith.science/pith/DWJFRI6HNPZX2FPMWNWYQ6JNVV.json","view_paper":"https://pith.science/paper/DWJFRI6H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.11658&json=true","fetch_graph":"https://pith.science/api/pith-number/DWJFRI6HNPZX2FPMWNWYQ6JNVV/graph.json","fetch_events":"https://pith.science/api/pith-number/DWJFRI6HNPZX2FPMWNWYQ6JNVV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DWJFRI6HNPZX2FPMWNWYQ6JNVV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DWJFRI6HNPZX2FPMWNWYQ6JNVV/action/storage_attestation","attest_author":"https://pith.science/pith/DWJFRI6HNPZX2FPMWNWYQ6JNVV/action/author_attestation","sign_citation":"https://pith.science/pith/DWJFRI6HNPZX2FPMWNWYQ6JNVV/action/citation_signature","submit_replication":"https://pith.science/pith/DWJFRI6HNPZX2FPMWNWYQ6JNVV/action/replication_record"}},"created_at":"2026-07-05T00:07:23.509407+00:00","updated_at":"2026-07-05T00:07:23.509407+00:00"}