{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:WOFFQIQ43ZWSNQRYNGNG2J3OEX","short_pith_number":"pith:WOFFQIQ4","canonical_record":{"source":{"id":"1804.06512","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-18T00:26:38Z","cross_cats_sorted":[],"title_canon_sha256":"4da3fe595531c6cdb9b66b6d7e47d3b68e0b733151880483f7a7eae6b8f20819","abstract_canon_sha256":"ef0d24159034137799839cde7323b4cdb8ae904a90d0c1f095c2893d65ac2392"},"schema_version":"1.0"},"canonical_sha256":"b38a58221cde6d26c238699a6d276e25c91409627ead000c567e61e300464659","source":{"kind":"arxiv","id":"1804.06512","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.06512","created_at":"2026-05-18T00:18:06Z"},{"alias_kind":"arxiv_version","alias_value":"1804.06512v1","created_at":"2026-05-18T00:18:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.06512","created_at":"2026-05-18T00:18:06Z"},{"alias_kind":"pith_short_12","alias_value":"WOFFQIQ43ZWS","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"WOFFQIQ43ZWSNQRY","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"WOFFQIQ4","created_at":"2026-05-18T12:33:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:WOFFQIQ43ZWSNQRYNGNG2J3OEX","target":"record","payload":{"canonical_record":{"source":{"id":"1804.06512","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-18T00:26:38Z","cross_cats_sorted":[],"title_canon_sha256":"4da3fe595531c6cdb9b66b6d7e47d3b68e0b733151880483f7a7eae6b8f20819","abstract_canon_sha256":"ef0d24159034137799839cde7323b4cdb8ae904a90d0c1f095c2893d65ac2392"},"schema_version":"1.0"},"canonical_sha256":"b38a58221cde6d26c238699a6d276e25c91409627ead000c567e61e300464659","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:18:06.424084Z","signature_b64":"PVzQEEnZbVVZiKJ+ewfG9HO30xE6U6BWSAf+JVJ73P9G0E+vo+H1JNd/sS69AW7vNthzm60KbNQ5G8O1r/bNAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b38a58221cde6d26c238699a6d276e25c91409627ead000c567e61e300464659","last_reissued_at":"2026-05-18T00:18:06.423524Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:18:06.423524Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1804.06512","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:18:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hjBM4qpW4JjZXBZGbT0qeA+Xa1BjOwygrSGghAKxtc5YMf8D3B4pQLlP0vxWFP2z9zyCnQ05DsgnqnyDlZZCCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T04:49:30.841270Z"},"content_sha256":"440e17367aca46941fbfef7ec52c02feb96b3cf2db534e5160e03cf447fb13b1","schema_version":"1.0","event_id":"sha256:440e17367aca46941fbfef7ec52c02feb96b3cf2db534e5160e03cf447fb13b1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:WOFFQIQ43ZWSNQRYNGNG2J3OEX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Dialogue Learning with Human Teaching and Feedback in End-to-End Trainable Task-Oriented Dialogue Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bing Liu, Dilek Hakkani-Tur, Gokhan Tur, Larry Heck, Pararth Shah","submitted_at":"2018-04-18T00:26:38Z","abstract_excerpt":"In this work, we present a hybrid learning method for training task-oriented dialogue systems through online user interactions. Popular methods for learning task-oriented dialogues include applying reinforcement learning with user feedback on supervised pre-training models. Efficiency of such learning method may suffer from the mismatch of dialogue state distribution between offline training and online interactive learning stages. To address this challenge, we propose a hybrid imitation and reinforcement learning method, with which a dialogue agent can effectively learn from its interaction wi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.06512","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:18:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i6q6gJKFKAD5AveTfzxoYs9Z73Novv3VNaoshFqe9eTG3GJ+DPPKzUcJhgckZKltleIQJwO7CJ+YMxCUp3EwCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T04:49:30.841974Z"},"content_sha256":"2153b9b6b2316e32e9e9fc00db3dc7ea4a1d3cffaeb4cb2e413f683bf25d65ee","schema_version":"1.0","event_id":"sha256:2153b9b6b2316e32e9e9fc00db3dc7ea4a1d3cffaeb4cb2e413f683bf25d65ee"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WOFFQIQ43ZWSNQRYNGNG2J3OEX/bundle.json","state_url":"https://pith.science/pith/WOFFQIQ43ZWSNQRYNGNG2J3OEX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WOFFQIQ43ZWSNQRYNGNG2J3OEX/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-27T04:49:30Z","links":{"resolver":"https://pith.science/pith/WOFFQIQ43ZWSNQRYNGNG2J3OEX","bundle":"https://pith.science/pith/WOFFQIQ43ZWSNQRYNGNG2J3OEX/bundle.json","state":"https://pith.science/pith/WOFFQIQ43ZWSNQRYNGNG2J3OEX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WOFFQIQ43ZWSNQRYNGNG2J3OEX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:WOFFQIQ43ZWSNQRYNGNG2J3OEX","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":"ef0d24159034137799839cde7323b4cdb8ae904a90d0c1f095c2893d65ac2392","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-18T00:26:38Z","title_canon_sha256":"4da3fe595531c6cdb9b66b6d7e47d3b68e0b733151880483f7a7eae6b8f20819"},"schema_version":"1.0","source":{"id":"1804.06512","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.06512","created_at":"2026-05-18T00:18:06Z"},{"alias_kind":"arxiv_version","alias_value":"1804.06512v1","created_at":"2026-05-18T00:18:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.06512","created_at":"2026-05-18T00:18:06Z"},{"alias_kind":"pith_short_12","alias_value":"WOFFQIQ43ZWS","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"WOFFQIQ43ZWSNQRY","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"WOFFQIQ4","created_at":"2026-05-18T12:33:01Z"}],"graph_snapshots":[{"event_id":"sha256:2153b9b6b2316e32e9e9fc00db3dc7ea4a1d3cffaeb4cb2e413f683bf25d65ee","target":"graph","created_at":"2026-05-18T00:18:06Z","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":"In this work, we present a hybrid learning method for training task-oriented dialogue systems through online user interactions. Popular methods for learning task-oriented dialogues include applying reinforcement learning with user feedback on supervised pre-training models. Efficiency of such learning method may suffer from the mismatch of dialogue state distribution between offline training and online interactive learning stages. To address this challenge, we propose a hybrid imitation and reinforcement learning method, with which a dialogue agent can effectively learn from its interaction wi","authors_text":"Bing Liu, Dilek Hakkani-Tur, Gokhan Tur, Larry Heck, Pararth Shah","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-18T00:26:38Z","title":"Dialogue Learning with Human Teaching and Feedback in End-to-End Trainable Task-Oriented Dialogue Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.06512","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":"sha256:440e17367aca46941fbfef7ec52c02feb96b3cf2db534e5160e03cf447fb13b1","target":"record","created_at":"2026-05-18T00:18:06Z","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":"ef0d24159034137799839cde7323b4cdb8ae904a90d0c1f095c2893d65ac2392","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-18T00:26:38Z","title_canon_sha256":"4da3fe595531c6cdb9b66b6d7e47d3b68e0b733151880483f7a7eae6b8f20819"},"schema_version":"1.0","source":{"id":"1804.06512","kind":"arxiv","version":1}},"canonical_sha256":"b38a58221cde6d26c238699a6d276e25c91409627ead000c567e61e300464659","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b38a58221cde6d26c238699a6d276e25c91409627ead000c567e61e300464659","first_computed_at":"2026-05-18T00:18:06.423524Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:18:06.423524Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PVzQEEnZbVVZiKJ+ewfG9HO30xE6U6BWSAf+JVJ73P9G0E+vo+H1JNd/sS69AW7vNthzm60KbNQ5G8O1r/bNAA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:18:06.424084Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.06512","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:440e17367aca46941fbfef7ec52c02feb96b3cf2db534e5160e03cf447fb13b1","sha256:2153b9b6b2316e32e9e9fc00db3dc7ea4a1d3cffaeb4cb2e413f683bf25d65ee"],"state_sha256":"1039ca2df701a94139c567876557e3ec923a783d9ac84ee66b73756a5f328c82"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"18o4OLrUbXcx9CKyP/TED3s1vfaGzF4iFy9fR/zAy4nuPu4jANZXfMO1oPtBNfXk2FuRtLVU+ghzPttPB5NrCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T04:49:30.845686Z","bundle_sha256":"7b3952240bce6f67772d0386756e5157f254818fd126908a2008286c8f4a1cef"}}