{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:FNPYGVT4VERSQWNMV4JCLGAXFK","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":"f31f72cf1d20e0d5e666e94954a2ecd37c068f04229f2fb6505b17a08549e154","cross_cats_sorted":["cs.CL","cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-08-27T17:06:15Z","title_canon_sha256":"30425773e188d7bafa537bae499cad697983c709d0537a7ac4b2ab985cd45b9b"},"schema_version":"1.0","source":{"id":"1908.10331","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.10331","created_at":"2026-07-05T00:00:11Z"},{"alias_kind":"arxiv_version","alias_value":"1908.10331v1","created_at":"2026-07-05T00:00:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.10331","created_at":"2026-07-05T00:00:11Z"},{"alias_kind":"pith_short_12","alias_value":"FNPYGVT4VERS","created_at":"2026-07-05T00:00:11Z"},{"alias_kind":"pith_short_16","alias_value":"FNPYGVT4VERSQWNM","created_at":"2026-07-05T00:00:11Z"},{"alias_kind":"pith_short_8","alias_value":"FNPYGVT4","created_at":"2026-07-05T00:00:11Z"}],"graph_snapshots":[{"event_id":"sha256:5fd1b6aecd1c29d08f1658df54cf807446a9de57d748d76c7c6f11d5703b4a77","target":"graph","created_at":"2026-07-05T00:00:11Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1908.10331/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Donghyeon Lee, Heriberto Cuay\\'ahuitl, Inchul Hwang, Jihie Kim, Seonghan Ryu, Sungja Choi","cross_cats":["cs.CL","cs.LG","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-08-27T17:06:15Z","title":"Deep Reinforcement Learning for Chatbots Using Clustered Actions and Human-Likeness Rewards"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.10331","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":"sha256:5f6a2aab0cc4483a410ef51e590dec83a0b9eee1e7c74052487b546cd96a1a73","target":"record","created_at":"2026-07-05T00:00:11Z","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":"f31f72cf1d20e0d5e666e94954a2ecd37c068f04229f2fb6505b17a08549e154","cross_cats_sorted":["cs.CL","cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-08-27T17:06:15Z","title_canon_sha256":"30425773e188d7bafa537bae499cad697983c709d0537a7ac4b2ab985cd45b9b"},"schema_version":"1.0","source":{"id":"1908.10331","kind":"arxiv","version":1}},"canonical_sha256":"2b5f83567ca9232859acaf122598172a8078a13fd02cd035e803f2c2fc1ca41e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2b5f83567ca9232859acaf122598172a8078a13fd02cd035e803f2c2fc1ca41e","first_computed_at":"2026-07-05T00:00:11.103877Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:00:11.103877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"M2KN9WL3PHZn/2W8t5Onm5xDPElSqtH5u2jO74T+Nlh68P7pdxckNg9C1pmxEnFwJjGnjkW5Kgt9B3At5VQNCg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:00:11.104291Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.10331","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5f6a2aab0cc4483a410ef51e590dec83a0b9eee1e7c74052487b546cd96a1a73","sha256:5fd1b6aecd1c29d08f1658df54cf807446a9de57d748d76c7c6f11d5703b4a77"],"state_sha256":"05f3a01f60adf2e47156063f277da7b46965dcb18039a60caac7e1ceebfefde1"}