{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:UESA24WWL4TFKHXX7QVFP636TX","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"26a0dbe0086ddabf820dbaefad82f8b57bd4a3ae16ba3e9e45bf523ae1baa47c","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-12-09T16:05:43Z","title_canon_sha256":"5e869f315b06dd79d61de52444997945be8d04f5951a160f489e5d3185c65435"},"schema_version":"1.0","source":{"id":"1812.03509","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.03509","created_at":"2026-05-17T23:58:46Z"},{"alias_kind":"arxiv_version","alias_value":"1812.03509v1","created_at":"2026-05-17T23:58:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.03509","created_at":"2026-05-17T23:58:46Z"},{"alias_kind":"pith_short_12","alias_value":"UESA24WWL4TF","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"UESA24WWL4TFKHXX","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"UESA24WW","created_at":"2026-05-18T12:32:56Z"}],"graph_snapshots":[{"event_id":"sha256:a187239f402660ab4728e5004eb5d33e9fa2e145efa671d19a534e2710b07ae7","target":"graph","created_at":"2026-05-17T23:58:46Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Julia Kiseleva, Maarten de Rijke, Ziming Li","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-12-09T16:05:43Z","title":"Dialogue Generation: From Imitation Learning to Inverse Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.03509","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:654278b035651da73077166edfeabce73026e33480c4ca950dedf91e13d2f369","target":"record","created_at":"2026-05-17T23:58:46Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"26a0dbe0086ddabf820dbaefad82f8b57bd4a3ae16ba3e9e45bf523ae1baa47c","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-12-09T16:05:43Z","title_canon_sha256":"5e869f315b06dd79d61de52444997945be8d04f5951a160f489e5d3185c65435"},"schema_version":"1.0","source":{"id":"1812.03509","kind":"arxiv","version":1}},"canonical_sha256":"a1240d72d65f26551ef7fc2a57fb7e9df176f0f2f260b2048e0c100e456851a3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a1240d72d65f26551ef7fc2a57fb7e9df176f0f2f260b2048e0c100e456851a3","first_computed_at":"2026-05-17T23:58:46.107242Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:58:46.107242Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"M69+JqehLMUjdW67FenGyfAesDXG9Bw9RSLXhHuU5Ms7mWJ2R6Hl5eMhQv8NJYq8/VbnVi4a4T9Mtu3wOwOxBg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:58:46.107790Z","signed_message":"canonical_sha256_bytes"},"source_id":"1812.03509","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:654278b035651da73077166edfeabce73026e33480c4ca950dedf91e13d2f369","sha256:a187239f402660ab4728e5004eb5d33e9fa2e145efa671d19a534e2710b07ae7"],"state_sha256":"3c2c893fcf222ba949fb8556acaf1d337fa6ef4b864f67f69bc1c6c1c3abc2b1"}