{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:F3ABSF5OETUKNE6E4RCJO4KNAJ","short_pith_number":"pith:F3ABSF5O","schema_version":"1.0","canonical_sha256":"2ec01917ae24e8a693c4e44497714d025838329a9e4749444a9bcbdbff66f8ed","source":{"kind":"arxiv","id":"1908.06136","version":2},"attestation_state":"computed","paper":{"title":"Transductive Auxiliary Task Self-Training for Neural Multi-Task Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Isabelle Augenstein, Johannes Bjerva, Katharina Kann","submitted_at":"2019-08-16T19:31:13Z","abstract_excerpt":"Multi-task learning and self-training are two common ways to improve a machine learning model's performance in settings with limited training data. Drawing heavily on ideas from those two approaches, we suggest transductive auxiliary task self-training: training a multi-task model on (i) a combination of main and auxiliary task training data, and (ii) test instances with auxiliary task labels which a single-task version of the model has previously generated. We perform extensive experiments on 86 combinations of languages and tasks. Our results are that, on average, transductive auxiliary task"},"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":"1908.06136","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-16T19:31:13Z","cross_cats_sorted":[],"title_canon_sha256":"0dcdb85e94ae9f48cb74c84448ab22a29ef44c4c534ee0188ad0fedc0e4a7e97","abstract_canon_sha256":"566bbed50e33d11b8eb0126def5fc0f2d33aca5a8867f2dd6eceed0972887f2e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:06:10.523680Z","signature_b64":"xWy2Q2+ksNA8b073SFXA97s7Aw7bpHMpBlMsxuEmLRImDsYvM+jiZRuskxMWXKaA6M+tGkmJPu1MzmCBOmgvDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ec01917ae24e8a693c4e44497714d025838329a9e4749444a9bcbdbff66f8ed","last_reissued_at":"2026-07-05T00:06:10.523221Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:06:10.523221Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transductive Auxiliary Task Self-Training for Neural Multi-Task Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Isabelle Augenstein, Johannes Bjerva, Katharina Kann","submitted_at":"2019-08-16T19:31:13Z","abstract_excerpt":"Multi-task learning and self-training are two common ways to improve a machine learning model's performance in settings with limited training data. Drawing heavily on ideas from those two approaches, we suggest transductive auxiliary task self-training: training a multi-task model on (i) a combination of main and auxiliary task training data, and (ii) test instances with auxiliary task labels which a single-task version of the model has previously generated. We perform extensive experiments on 86 combinations of languages and tasks. Our results are that, on average, transductive auxiliary task"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.06136","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/1908.06136/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":"1908.06136","created_at":"2026-07-05T00:06:10.523276+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.06136v2","created_at":"2026-07-05T00:06:10.523276+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.06136","created_at":"2026-07-05T00:06:10.523276+00:00"},{"alias_kind":"pith_short_12","alias_value":"F3ABSF5OETUK","created_at":"2026-07-05T00:06:10.523276+00:00"},{"alias_kind":"pith_short_16","alias_value":"F3ABSF5OETUKNE6E","created_at":"2026-07-05T00:06:10.523276+00:00"},{"alias_kind":"pith_short_8","alias_value":"F3ABSF5O","created_at":"2026-07-05T00:06:10.523276+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/F3ABSF5OETUKNE6E4RCJO4KNAJ","json":"https://pith.science/pith/F3ABSF5OETUKNE6E4RCJO4KNAJ.json","graph_json":"https://pith.science/api/pith-number/F3ABSF5OETUKNE6E4RCJO4KNAJ/graph.json","events_json":"https://pith.science/api/pith-number/F3ABSF5OETUKNE6E4RCJO4KNAJ/events.json","paper":"https://pith.science/paper/F3ABSF5O"},"agent_actions":{"view_html":"https://pith.science/pith/F3ABSF5OETUKNE6E4RCJO4KNAJ","download_json":"https://pith.science/pith/F3ABSF5OETUKNE6E4RCJO4KNAJ.json","view_paper":"https://pith.science/paper/F3ABSF5O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.06136&json=true","fetch_graph":"https://pith.science/api/pith-number/F3ABSF5OETUKNE6E4RCJO4KNAJ/graph.json","fetch_events":"https://pith.science/api/pith-number/F3ABSF5OETUKNE6E4RCJO4KNAJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F3ABSF5OETUKNE6E4RCJO4KNAJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F3ABSF5OETUKNE6E4RCJO4KNAJ/action/storage_attestation","attest_author":"https://pith.science/pith/F3ABSF5OETUKNE6E4RCJO4KNAJ/action/author_attestation","sign_citation":"https://pith.science/pith/F3ABSF5OETUKNE6E4RCJO4KNAJ/action/citation_signature","submit_replication":"https://pith.science/pith/F3ABSF5OETUKNE6E4RCJO4KNAJ/action/replication_record"}},"created_at":"2026-07-05T00:06:10.523276+00:00","updated_at":"2026-07-05T00:06:10.523276+00:00"}