{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2011:DQC5FZQWVKD7APFTF2T2BBDYYV","short_pith_number":"pith:DQC5FZQW","schema_version":"1.0","canonical_sha256":"1c05d2e616aa87f03cb32ea7a08478c574d455fecfd86ba41f76f6459272a600","source":{"kind":"arxiv","id":"1106.0676","version":1},"attestation_state":"computed","paper":{"title":"Optimizing Dialogue Management with Reinforcement Learning: Experiments with the NJFun System","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"D. Litman, M. Kearns, M. Walker, S. Singh","submitted_at":"2011-06-03T14:55:23Z","abstract_excerpt":"Designing the dialogue policy of a spoken dialogue system    involves many nontrivial choices.  This paper presents a reinforcement    learning approach for automatically optimizing a dialogue policy,    which addresses the technical challenges in applying reinforcement    learning to a working dialogue system with human users.  We report on    the design, construction and empirical evaluation of NJFun, an    experimental spoken dialogue system that provides users with access to    information about fun things to do in New Jersey.  Our results show    that by optimizing its performance via rei"},"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":"1106.0676","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2011-06-03T14:55:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4c057189250a19890cac5c11492812bbc842d838b9ab01b5806c87170bc5ce8b","abstract_canon_sha256":"e78d86ffe0b416484ec9bb874ffbdce17b7e4ffe4c92c093c8b03a37ed235f63"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:20:39.769122Z","signature_b64":"yv9Lo2NkQGsz4ZQ+Kn6TSnvv3iv7ZC8G6u2cOmzzjcSs/Bl760mxDDHsgkJ++xQQOFcozdStbvLwZMBS+P0zDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c05d2e616aa87f03cb32ea7a08478c574d455fecfd86ba41f76f6459272a600","last_reissued_at":"2026-05-18T04:20:39.768384Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:20:39.768384Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimizing Dialogue Management with Reinforcement Learning: Experiments with the NJFun System","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"D. Litman, M. Kearns, M. Walker, S. Singh","submitted_at":"2011-06-03T14:55:23Z","abstract_excerpt":"Designing the dialogue policy of a spoken dialogue system    involves many nontrivial choices.  This paper presents a reinforcement    learning approach for automatically optimizing a dialogue policy,    which addresses the technical challenges in applying reinforcement    learning to a working dialogue system with human users.  We report on    the design, construction and empirical evaluation of NJFun, an    experimental spoken dialogue system that provides users with access to    information about fun things to do in New Jersey.  Our results show    that by optimizing its performance via rei"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1106.0676","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1106.0676","created_at":"2026-05-18T04:20:39.768509+00:00"},{"alias_kind":"arxiv_version","alias_value":"1106.0676v1","created_at":"2026-05-18T04:20:39.768509+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1106.0676","created_at":"2026-05-18T04:20:39.768509+00:00"},{"alias_kind":"pith_short_12","alias_value":"DQC5FZQWVKD7","created_at":"2026-05-18T12:26:26.731475+00:00"},{"alias_kind":"pith_short_16","alias_value":"DQC5FZQWVKD7APFT","created_at":"2026-05-18T12:26:26.731475+00:00"},{"alias_kind":"pith_short_8","alias_value":"DQC5FZQW","created_at":"2026-05-18T12:26:26.731475+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/DQC5FZQWVKD7APFTF2T2BBDYYV","json":"https://pith.science/pith/DQC5FZQWVKD7APFTF2T2BBDYYV.json","graph_json":"https://pith.science/api/pith-number/DQC5FZQWVKD7APFTF2T2BBDYYV/graph.json","events_json":"https://pith.science/api/pith-number/DQC5FZQWVKD7APFTF2T2BBDYYV/events.json","paper":"https://pith.science/paper/DQC5FZQW"},"agent_actions":{"view_html":"https://pith.science/pith/DQC5FZQWVKD7APFTF2T2BBDYYV","download_json":"https://pith.science/pith/DQC5FZQWVKD7APFTF2T2BBDYYV.json","view_paper":"https://pith.science/paper/DQC5FZQW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1106.0676&json=true","fetch_graph":"https://pith.science/api/pith-number/DQC5FZQWVKD7APFTF2T2BBDYYV/graph.json","fetch_events":"https://pith.science/api/pith-number/DQC5FZQWVKD7APFTF2T2BBDYYV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DQC5FZQWVKD7APFTF2T2BBDYYV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DQC5FZQWVKD7APFTF2T2BBDYYV/action/storage_attestation","attest_author":"https://pith.science/pith/DQC5FZQWVKD7APFTF2T2BBDYYV/action/author_attestation","sign_citation":"https://pith.science/pith/DQC5FZQWVKD7APFTF2T2BBDYYV/action/citation_signature","submit_replication":"https://pith.science/pith/DQC5FZQWVKD7APFTF2T2BBDYYV/action/replication_record"}},"created_at":"2026-05-18T04:20:39.768509+00:00","updated_at":"2026-05-18T04:20:39.768509+00:00"}