{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:PJBUN2KA4O2MZI4ROJS2TBTITV","short_pith_number":"pith:PJBUN2KA","schema_version":"1.0","canonical_sha256":"7a4346e940e3b4cca3917265a986689d4fdd3fa8bb0879670e92ca4da5484e20","source":{"kind":"arxiv","id":"1709.02349","version":2},"attestation_state":"computed","paper":{"title":"A Deep Reinforcement Learning Chatbot","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.NE","stat.ML"],"primary_cat":"cs.CL","authors_text":"Alexandre de Brebisson, Alexandre Nguyen, Chinnadhurai Sankar, Dendi Suhubdy, Iulian V. Serban, Joelle Pineau, Jose M. R. Sotelo, Mathieu Germain, Michael Pieper, Nan Rosemary Ke, Sai Rajeshwar, Saizheng Zhang, Sandeep Subramanian, Sarath Chandar, Taesup Kim, Vincent Michalski, Yoshua Bengio, Zhouhan Lin","submitted_at":"2017-09-07T16:51:09Z","abstract_excerpt":"We present MILABOT: a deep reinforcement learning chatbot developed by the Montreal Institute for Learning Algorithms (MILA) for the Amazon Alexa Prize competition. MILABOT is capable of conversing with humans on popular small talk topics through both speech and text. The system consists of an ensemble of natural language generation and retrieval models, including template-based models, bag-of-words models, sequence-to-sequence neural network and latent variable neural network models. By applying reinforcement learning to crowdsourced data and real-world user interactions, the system has been "},"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":"1709.02349","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-09-07T16:51:09Z","cross_cats_sorted":["cs.AI","cs.LG","cs.NE","stat.ML"],"title_canon_sha256":"eb333e8ce922249ed3f6381b3a3f65d04f4ae0d9e412f20f30a8e134021c1025","abstract_canon_sha256":"99c0cc166e3cb143b8aa1bb93008dfecf367f690c842941b9a9730054419e2cd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:31:18.741725Z","signature_b64":"TGtjT1OB0dHXPsvUR1+DkpPo1AlgYOpWKGbigAEZ0IpXVTc05G//OeFDLNfyRuSupX4wkTTAsuMfJdXh4wGTDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a4346e940e3b4cca3917265a986689d4fdd3fa8bb0879670e92ca4da5484e20","last_reissued_at":"2026-05-18T00:31:18.740953Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:31:18.740953Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Deep Reinforcement Learning Chatbot","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.NE","stat.ML"],"primary_cat":"cs.CL","authors_text":"Alexandre de Brebisson, Alexandre Nguyen, Chinnadhurai Sankar, Dendi Suhubdy, Iulian V. Serban, Joelle Pineau, Jose M. R. Sotelo, Mathieu Germain, Michael Pieper, Nan Rosemary Ke, Sai Rajeshwar, Saizheng Zhang, Sandeep Subramanian, Sarath Chandar, Taesup Kim, Vincent Michalski, Yoshua Bengio, Zhouhan Lin","submitted_at":"2017-09-07T16:51:09Z","abstract_excerpt":"We present MILABOT: a deep reinforcement learning chatbot developed by the Montreal Institute for Learning Algorithms (MILA) for the Amazon Alexa Prize competition. MILABOT is capable of conversing with humans on popular small talk topics through both speech and text. The system consists of an ensemble of natural language generation and retrieval models, including template-based models, bag-of-words models, sequence-to-sequence neural network and latent variable neural network models. By applying reinforcement learning to crowdsourced data and real-world user interactions, the system has been "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.02349","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":""},"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":"1709.02349","created_at":"2026-05-18T00:31:18.741081+00:00"},{"alias_kind":"arxiv_version","alias_value":"1709.02349v2","created_at":"2026-05-18T00:31:18.741081+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.02349","created_at":"2026-05-18T00:31:18.741081+00:00"},{"alias_kind":"pith_short_12","alias_value":"PJBUN2KA4O2M","created_at":"2026-05-18T12:31:37.085036+00:00"},{"alias_kind":"pith_short_16","alias_value":"PJBUN2KA4O2MZI4R","created_at":"2026-05-18T12:31:37.085036+00:00"},{"alias_kind":"pith_short_8","alias_value":"PJBUN2KA","created_at":"2026-05-18T12:31:37.085036+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"1906.09774","citing_title":"Emotionally-Aware Chatbots: A Survey","ref_index":49,"is_internal_anchor":true},{"citing_arxiv_id":"1907.00456","citing_title":"Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog","ref_index":51,"is_internal_anchor":true},{"citing_arxiv_id":"2306.08543","citing_title":"MiniLLM: On-Policy Distillation of Large Language Models","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PJBUN2KA4O2MZI4ROJS2TBTITV","json":"https://pith.science/pith/PJBUN2KA4O2MZI4ROJS2TBTITV.json","graph_json":"https://pith.science/api/pith-number/PJBUN2KA4O2MZI4ROJS2TBTITV/graph.json","events_json":"https://pith.science/api/pith-number/PJBUN2KA4O2MZI4ROJS2TBTITV/events.json","paper":"https://pith.science/paper/PJBUN2KA"},"agent_actions":{"view_html":"https://pith.science/pith/PJBUN2KA4O2MZI4ROJS2TBTITV","download_json":"https://pith.science/pith/PJBUN2KA4O2MZI4ROJS2TBTITV.json","view_paper":"https://pith.science/paper/PJBUN2KA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1709.02349&json=true","fetch_graph":"https://pith.science/api/pith-number/PJBUN2KA4O2MZI4ROJS2TBTITV/graph.json","fetch_events":"https://pith.science/api/pith-number/PJBUN2KA4O2MZI4ROJS2TBTITV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PJBUN2KA4O2MZI4ROJS2TBTITV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PJBUN2KA4O2MZI4ROJS2TBTITV/action/storage_attestation","attest_author":"https://pith.science/pith/PJBUN2KA4O2MZI4ROJS2TBTITV/action/author_attestation","sign_citation":"https://pith.science/pith/PJBUN2KA4O2MZI4ROJS2TBTITV/action/citation_signature","submit_replication":"https://pith.science/pith/PJBUN2KA4O2MZI4ROJS2TBTITV/action/replication_record"}},"created_at":"2026-05-18T00:31:18.741081+00:00","updated_at":"2026-05-18T00:31:18.741081+00:00"}