{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:UESA24WWL4TFKHXX7QVFP636TX","short_pith_number":"pith:UESA24WW","schema_version":"1.0","canonical_sha256":"a1240d72d65f26551ef7fc2a57fb7e9df176f0f2f260b2048e0c100e456851a3","source":{"kind":"arxiv","id":"1812.03509","version":1},"attestation_state":"computed","paper":{"title":"Dialogue Generation: From Imitation Learning to Inverse Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Julia Kiseleva, Maarten de Rijke, Ziming Li","submitted_at":"2018-12-09T16:05:43Z","abstract_excerpt":"The performance of adversarial dialogue generation models relies on the quality of the reward signal produced by the discriminator. The reward signal from a poor discriminator can be very sparse and unstable, which may lead the generator to fall into a local optimum or to produce nonsense replies. To alleviate the first problem, we first extend a recently proposed adversarial dialogue generation method to an adversarial imitation learning solution. Then, in the framework of adversarial inverse reinforcement learning, we propose a new reward model for dialogue generation that can provide a more"},"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":"1812.03509","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-12-09T16:05:43Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"5e869f315b06dd79d61de52444997945be8d04f5951a160f489e5d3185c65435","abstract_canon_sha256":"26a0dbe0086ddabf820dbaefad82f8b57bd4a3ae16ba3e9e45bf523ae1baa47c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:58:46.107790Z","signature_b64":"M69+JqehLMUjdW67FenGyfAesDXG9Bw9RSLXhHuU5Ms7mWJ2R6Hl5eMhQv8NJYq8/VbnVi4a4T9Mtu3wOwOxBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1240d72d65f26551ef7fc2a57fb7e9df176f0f2f260b2048e0c100e456851a3","last_reissued_at":"2026-05-17T23:58:46.107242Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:58:46.107242Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dialogue Generation: From Imitation Learning to Inverse Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Julia Kiseleva, Maarten de Rijke, Ziming Li","submitted_at":"2018-12-09T16:05:43Z","abstract_excerpt":"The performance of adversarial dialogue generation models relies on the quality of the reward signal produced by the discriminator. The reward signal from a poor discriminator can be very sparse and unstable, which may lead the generator to fall into a local optimum or to produce nonsense replies. To alleviate the first problem, we first extend a recently proposed adversarial dialogue generation method to an adversarial imitation learning solution. Then, in the framework of adversarial inverse reinforcement learning, we propose a new reward model for dialogue generation that can provide a more"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.03509","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":"1812.03509","created_at":"2026-05-17T23:58:46.107330+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.03509v1","created_at":"2026-05-17T23:58:46.107330+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.03509","created_at":"2026-05-17T23:58:46.107330+00:00"},{"alias_kind":"pith_short_12","alias_value":"UESA24WWL4TF","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_16","alias_value":"UESA24WWL4TFKHXX","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_8","alias_value":"UESA24WW","created_at":"2026-05-18T12:32:56.356000+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.00456","citing_title":"Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UESA24WWL4TFKHXX7QVFP636TX","json":"https://pith.science/pith/UESA24WWL4TFKHXX7QVFP636TX.json","graph_json":"https://pith.science/api/pith-number/UESA24WWL4TFKHXX7QVFP636TX/graph.json","events_json":"https://pith.science/api/pith-number/UESA24WWL4TFKHXX7QVFP636TX/events.json","paper":"https://pith.science/paper/UESA24WW"},"agent_actions":{"view_html":"https://pith.science/pith/UESA24WWL4TFKHXX7QVFP636TX","download_json":"https://pith.science/pith/UESA24WWL4TFKHXX7QVFP636TX.json","view_paper":"https://pith.science/paper/UESA24WW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.03509&json=true","fetch_graph":"https://pith.science/api/pith-number/UESA24WWL4TFKHXX7QVFP636TX/graph.json","fetch_events":"https://pith.science/api/pith-number/UESA24WWL4TFKHXX7QVFP636TX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UESA24WWL4TFKHXX7QVFP636TX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UESA24WWL4TFKHXX7QVFP636TX/action/storage_attestation","attest_author":"https://pith.science/pith/UESA24WWL4TFKHXX7QVFP636TX/action/author_attestation","sign_citation":"https://pith.science/pith/UESA24WWL4TFKHXX7QVFP636TX/action/citation_signature","submit_replication":"https://pith.science/pith/UESA24WWL4TFKHXX7QVFP636TX/action/replication_record"}},"created_at":"2026-05-17T23:58:46.107330+00:00","updated_at":"2026-05-17T23:58:46.107330+00:00"}