{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:FNPYGVT4VERSQWNMV4JCLGAXFK","short_pith_number":"pith:FNPYGVT4","schema_version":"1.0","canonical_sha256":"2b5f83567ca9232859acaf122598172a8078a13fd02cd035e803f2c2fc1ca41e","source":{"kind":"arxiv","id":"1908.10331","version":1},"attestation_state":"computed","paper":{"title":"Deep Reinforcement Learning for Chatbots Using Clustered Actions and Human-Likeness Rewards","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.NE"],"primary_cat":"cs.AI","authors_text":"Donghyeon Lee, Heriberto Cuay\\'ahuitl, Inchul Hwang, Jihie Kim, Seonghan Ryu, Sungja Choi","submitted_at":"2019-08-27T17:06:15Z","abstract_excerpt":"Training chatbots using the reinforcement learning paradigm is challenging due to high-dimensional states, infinite action spaces and the difficulty in specifying the reward function. We address such problems using clustered actions instead of infinite actions, and a simple but promising reward function based on human-likeness scores derived from human-human dialogue data. We train Deep Reinforcement Learning (DRL) agents using chitchat data in raw text---without any manual annotations. Experimental results using different splits of training data report the following. First, that our agents le"},"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":"1908.10331","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-08-27T17:06:15Z","cross_cats_sorted":["cs.CL","cs.LG","cs.NE"],"title_canon_sha256":"30425773e188d7bafa537bae499cad697983c709d0537a7ac4b2ab985cd45b9b","abstract_canon_sha256":"f31f72cf1d20e0d5e666e94954a2ecd37c068f04229f2fb6505b17a08549e154"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:00:11.104291Z","signature_b64":"M2KN9WL3PHZn/2W8t5Onm5xDPElSqtH5u2jO74T+Nlh68P7pdxckNg9C1pmxEnFwJjGnjkW5Kgt9B3At5VQNCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b5f83567ca9232859acaf122598172a8078a13fd02cd035e803f2c2fc1ca41e","last_reissued_at":"2026-07-05T00:00:11.103877Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:00:11.103877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Reinforcement Learning for Chatbots Using Clustered Actions and Human-Likeness Rewards","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.NE"],"primary_cat":"cs.AI","authors_text":"Donghyeon Lee, Heriberto Cuay\\'ahuitl, Inchul Hwang, Jihie Kim, Seonghan Ryu, Sungja Choi","submitted_at":"2019-08-27T17:06:15Z","abstract_excerpt":"Training chatbots using the reinforcement learning paradigm is challenging due to high-dimensional states, infinite action spaces and the difficulty in specifying the reward function. We address such problems using clustered actions instead of infinite actions, and a simple but promising reward function based on human-likeness scores derived from human-human dialogue data. We train Deep Reinforcement Learning (DRL) agents using chitchat data in raw text---without any manual annotations. Experimental results using different splits of training data report the following. First, that our agents le"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.10331","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/1908.10331/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":"1908.10331","created_at":"2026-07-05T00:00:11.103941+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.10331v1","created_at":"2026-07-05T00:00:11.103941+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.10331","created_at":"2026-07-05T00:00:11.103941+00:00"},{"alias_kind":"pith_short_12","alias_value":"FNPYGVT4VERS","created_at":"2026-07-05T00:00:11.103941+00:00"},{"alias_kind":"pith_short_16","alias_value":"FNPYGVT4VERSQWNM","created_at":"2026-07-05T00:00:11.103941+00:00"},{"alias_kind":"pith_short_8","alias_value":"FNPYGVT4","created_at":"2026-07-05T00:00:11.103941+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FNPYGVT4VERSQWNMV4JCLGAXFK","json":"https://pith.science/pith/FNPYGVT4VERSQWNMV4JCLGAXFK.json","graph_json":"https://pith.science/api/pith-number/FNPYGVT4VERSQWNMV4JCLGAXFK/graph.json","events_json":"https://pith.science/api/pith-number/FNPYGVT4VERSQWNMV4JCLGAXFK/events.json","paper":"https://pith.science/paper/FNPYGVT4"},"agent_actions":{"view_html":"https://pith.science/pith/FNPYGVT4VERSQWNMV4JCLGAXFK","download_json":"https://pith.science/pith/FNPYGVT4VERSQWNMV4JCLGAXFK.json","view_paper":"https://pith.science/paper/FNPYGVT4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.10331&json=true","fetch_graph":"https://pith.science/api/pith-number/FNPYGVT4VERSQWNMV4JCLGAXFK/graph.json","fetch_events":"https://pith.science/api/pith-number/FNPYGVT4VERSQWNMV4JCLGAXFK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FNPYGVT4VERSQWNMV4JCLGAXFK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FNPYGVT4VERSQWNMV4JCLGAXFK/action/storage_attestation","attest_author":"https://pith.science/pith/FNPYGVT4VERSQWNMV4JCLGAXFK/action/author_attestation","sign_citation":"https://pith.science/pith/FNPYGVT4VERSQWNMV4JCLGAXFK/action/citation_signature","submit_replication":"https://pith.science/pith/FNPYGVT4VERSQWNMV4JCLGAXFK/action/replication_record"}},"created_at":"2026-07-05T00:00:11.103941+00:00","updated_at":"2026-07-05T00:00:11.103941+00:00"}