{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:4BQ4VBFZPBEKZ5TPTLQWD5OXQL","short_pith_number":"pith:4BQ4VBFZ","schema_version":"1.0","canonical_sha256":"e061ca84b97848acf66f9ae161f5d782d02d95af9102f9570b6a9d91173633a2","source":{"kind":"arxiv","id":"1910.09342","version":2},"attestation_state":"computed","paper":{"title":"Domain-agnostic Question-Answering with Adversarial Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Donggyu Kim, Jangwon Park, Seanie Lee","submitted_at":"2019-10-21T13:11:21Z","abstract_excerpt":"Adapting models to new domain without finetuning is a challenging problem in deep learning. In this paper, we utilize an adversarial training framework for domain generalization in Question Answering (QA) task. Our model consists of a conventional QA model and a discriminator. The training is performed in the adversarial manner, where the two models constantly compete, so that QA model can learn domain-invariant features. We apply this approach in MRQA Shared Task 2019 and show better performance compared to the baseline model."},"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":"1910.09342","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-10-21T13:11:21Z","cross_cats_sorted":[],"title_canon_sha256":"9d775fa6a16e15a1a96c937d82d703d1f92c756f3d87b0b9c2fa17395549598b","abstract_canon_sha256":"cfc45fa6a033da96336a6bc26f49c4b274ff9a41fd28124276233527f2432993"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:14:00.217209Z","signature_b64":"ON/exG60Aml2Yw7QJ+v5SD5Jlw2EVPlNw/y2wQPolE9hStqJ0ZMD06O+OKbo6bD81TngFuljm2k1SNOgyNbkDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e061ca84b97848acf66f9ae161f5d782d02d95af9102f9570b6a9d91173633a2","last_reissued_at":"2026-07-05T00:14:00.216811Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:14:00.216811Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Domain-agnostic Question-Answering with Adversarial Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Donggyu Kim, Jangwon Park, Seanie Lee","submitted_at":"2019-10-21T13:11:21Z","abstract_excerpt":"Adapting models to new domain without finetuning is a challenging problem in deep learning. In this paper, we utilize an adversarial training framework for domain generalization in Question Answering (QA) task. Our model consists of a conventional QA model and a discriminator. The training is performed in the adversarial manner, where the two models constantly compete, so that QA model can learn domain-invariant features. We apply this approach in MRQA Shared Task 2019 and show better performance compared to the baseline model."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.09342","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/1910.09342/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":"1910.09342","created_at":"2026-07-05T00:14:00.216869+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.09342v2","created_at":"2026-07-05T00:14:00.216869+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.09342","created_at":"2026-07-05T00:14:00.216869+00:00"},{"alias_kind":"pith_short_12","alias_value":"4BQ4VBFZPBEK","created_at":"2026-07-05T00:14:00.216869+00:00"},{"alias_kind":"pith_short_16","alias_value":"4BQ4VBFZPBEKZ5TP","created_at":"2026-07-05T00:14:00.216869+00:00"},{"alias_kind":"pith_short_8","alias_value":"4BQ4VBFZ","created_at":"2026-07-05T00:14:00.216869+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/4BQ4VBFZPBEKZ5TPTLQWD5OXQL","json":"https://pith.science/pith/4BQ4VBFZPBEKZ5TPTLQWD5OXQL.json","graph_json":"https://pith.science/api/pith-number/4BQ4VBFZPBEKZ5TPTLQWD5OXQL/graph.json","events_json":"https://pith.science/api/pith-number/4BQ4VBFZPBEKZ5TPTLQWD5OXQL/events.json","paper":"https://pith.science/paper/4BQ4VBFZ"},"agent_actions":{"view_html":"https://pith.science/pith/4BQ4VBFZPBEKZ5TPTLQWD5OXQL","download_json":"https://pith.science/pith/4BQ4VBFZPBEKZ5TPTLQWD5OXQL.json","view_paper":"https://pith.science/paper/4BQ4VBFZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.09342&json=true","fetch_graph":"https://pith.science/api/pith-number/4BQ4VBFZPBEKZ5TPTLQWD5OXQL/graph.json","fetch_events":"https://pith.science/api/pith-number/4BQ4VBFZPBEKZ5TPTLQWD5OXQL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4BQ4VBFZPBEKZ5TPTLQWD5OXQL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4BQ4VBFZPBEKZ5TPTLQWD5OXQL/action/storage_attestation","attest_author":"https://pith.science/pith/4BQ4VBFZPBEKZ5TPTLQWD5OXQL/action/author_attestation","sign_citation":"https://pith.science/pith/4BQ4VBFZPBEKZ5TPTLQWD5OXQL/action/citation_signature","submit_replication":"https://pith.science/pith/4BQ4VBFZPBEKZ5TPTLQWD5OXQL/action/replication_record"}},"created_at":"2026-07-05T00:14:00.216869+00:00","updated_at":"2026-07-05T00:14:00.216869+00:00"}