{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:MZ5A5PJGMWUJUEVWON65Z27DYC","short_pith_number":"pith:MZ5A5PJG","schema_version":"1.0","canonical_sha256":"667a0ebd2665a89a12b6737ddcebe3c0b964027ec2de6292abfdd2903fc61aa8","source":{"kind":"arxiv","id":"2104.08231","version":1},"attestation_state":"computed","paper":{"title":"An Adversarially-Learned Turing Test for Dialog Generation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bill Dolan, Michel Galley, Xiang Gao, Yizhe Zhang","submitted_at":"2021-04-16T17:13:14Z","abstract_excerpt":"The design of better automated dialogue evaluation metrics offers the potential of accelerate evaluation research on conversational AI. However, existing trainable dialogue evaluation models are generally restricted to classifiers trained in a purely supervised manner, which suffer a significant risk from adversarial attacking (e.g., a nonsensical response that enjoys a high classification score). To alleviate this risk, we propose an adversarial training approach to learn a robust model, ATT (Adversarial Turing Test), that discriminates machine-generated responses from human-written replies. "},"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":"2104.08231","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-16T17:13:14Z","cross_cats_sorted":[],"title_canon_sha256":"dac81226747ad06e64c6592dc85002e020876f2907542ae5cf0f00cb9acfbf9e","abstract_canon_sha256":"a43fdb5831af508e71948ab648c743c46b35fc3dfd485340307f6b2d4e4182e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:32:42.367410Z","signature_b64":"1EL4YuKWeZzfTygJ9w8rFOPHRAN1qqMcxj6QcrQtIkil113vH1h3+/l48ILQoOWByRQXxiEFnYIe1IHKCdP0BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"667a0ebd2665a89a12b6737ddcebe3c0b964027ec2de6292abfdd2903fc61aa8","last_reissued_at":"2026-07-05T02:32:42.366417Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:32:42.366417Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Adversarially-Learned Turing Test for Dialog Generation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bill Dolan, Michel Galley, Xiang Gao, Yizhe Zhang","submitted_at":"2021-04-16T17:13:14Z","abstract_excerpt":"The design of better automated dialogue evaluation metrics offers the potential of accelerate evaluation research on conversational AI. However, existing trainable dialogue evaluation models are generally restricted to classifiers trained in a purely supervised manner, which suffer a significant risk from adversarial attacking (e.g., a nonsensical response that enjoys a high classification score). To alleviate this risk, we propose an adversarial training approach to learn a robust model, ATT (Adversarial Turing Test), that discriminates machine-generated responses from human-written replies. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.08231","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2104.08231/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":"2104.08231","created_at":"2026-07-05T02:32:42.366916+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.08231v1","created_at":"2026-07-05T02:32:42.366916+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.08231","created_at":"2026-07-05T02:32:42.366916+00:00"},{"alias_kind":"pith_short_12","alias_value":"MZ5A5PJGMWUJ","created_at":"2026-07-05T02:32:42.366916+00:00"},{"alias_kind":"pith_short_16","alias_value":"MZ5A5PJGMWUJUEVW","created_at":"2026-07-05T02:32:42.366916+00:00"},{"alias_kind":"pith_short_8","alias_value":"MZ5A5PJG","created_at":"2026-07-05T02:32:42.366916+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30875","citing_title":"The Label Imitation Game: Turing Test Network for Zero-Shot Pseudo-Label Pruning","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MZ5A5PJGMWUJUEVWON65Z27DYC","json":"https://pith.science/pith/MZ5A5PJGMWUJUEVWON65Z27DYC.json","graph_json":"https://pith.science/api/pith-number/MZ5A5PJGMWUJUEVWON65Z27DYC/graph.json","events_json":"https://pith.science/api/pith-number/MZ5A5PJGMWUJUEVWON65Z27DYC/events.json","paper":"https://pith.science/paper/MZ5A5PJG"},"agent_actions":{"view_html":"https://pith.science/pith/MZ5A5PJGMWUJUEVWON65Z27DYC","download_json":"https://pith.science/pith/MZ5A5PJGMWUJUEVWON65Z27DYC.json","view_paper":"https://pith.science/paper/MZ5A5PJG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.08231&json=true","fetch_graph":"https://pith.science/api/pith-number/MZ5A5PJGMWUJUEVWON65Z27DYC/graph.json","fetch_events":"https://pith.science/api/pith-number/MZ5A5PJGMWUJUEVWON65Z27DYC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MZ5A5PJGMWUJUEVWON65Z27DYC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MZ5A5PJGMWUJUEVWON65Z27DYC/action/storage_attestation","attest_author":"https://pith.science/pith/MZ5A5PJGMWUJUEVWON65Z27DYC/action/author_attestation","sign_citation":"https://pith.science/pith/MZ5A5PJGMWUJUEVWON65Z27DYC/action/citation_signature","submit_replication":"https://pith.science/pith/MZ5A5PJGMWUJUEVWON65Z27DYC/action/replication_record"}},"created_at":"2026-07-05T02:32:42.366916+00:00","updated_at":"2026-07-05T02:32:42.366916+00:00"}