{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:T2UI65V2EJ3WFNB24FQSSNZGWN","short_pith_number":"pith:T2UI65V2","schema_version":"1.0","canonical_sha256":"9ea88f76ba227762b43ae161293726b34d4f7c94303c5f171e0ab463f86da9d9","source":{"kind":"arxiv","id":"2204.10198","version":2},"attestation_state":"computed","paper":{"title":"Context-Aware Language Modeling for Goal-Oriented Dialogue Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Charlie Snell, Justin Fu, Mengjiao Yang, Sergey Levine, Yi Su","submitted_at":"2022-04-18T17:23:11Z","abstract_excerpt":"Goal-oriented dialogue systems face a trade-off between fluent language generation and task-specific control. While supervised learning with large language models is capable of producing realistic text, how to steer such responses towards completing a specific task without sacrificing language quality remains an open question. In this work, we formulate goal-oriented dialogue as a partially observed Markov decision process, interpreting the language model as a representation of both the dynamics and the policy. This view allows us to extend techniques from learning-based control, such as task "},"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":"2204.10198","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-18T17:23:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"80b7bd64656b6783e245b76f33382f112d8df9d98102b4654f596324dcc23eba","abstract_canon_sha256":"a51a3e62324818995c6e81959e840fd81db1787e14981c024452c55fad687ab2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:16:55.785021Z","signature_b64":"9iE2sRwjziu2oAEI74SOGDAClgKazbZRjhLIqTybNptEHZbreosFQkUnLrPH+czwHhDj4HXtZeWvHhZSXOYDBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ea88f76ba227762b43ae161293726b34d4f7c94303c5f171e0ab463f86da9d9","last_reissued_at":"2026-07-05T04:16:55.784502Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:16:55.784502Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Context-Aware Language Modeling for Goal-Oriented Dialogue Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Charlie Snell, Justin Fu, Mengjiao Yang, Sergey Levine, Yi Su","submitted_at":"2022-04-18T17:23:11Z","abstract_excerpt":"Goal-oriented dialogue systems face a trade-off between fluent language generation and task-specific control. While supervised learning with large language models is capable of producing realistic text, how to steer such responses towards completing a specific task without sacrificing language quality remains an open question. In this work, we formulate goal-oriented dialogue as a partially observed Markov decision process, interpreting the language model as a representation of both the dynamics and the policy. This view allows us to extend techniques from learning-based control, such as task "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.10198","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2204.10198/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":"2204.10198","created_at":"2026-07-05T04:16:55.784558+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.10198v2","created_at":"2026-07-05T04:16:55.784558+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.10198","created_at":"2026-07-05T04:16:55.784558+00:00"},{"alias_kind":"pith_short_12","alias_value":"T2UI65V2EJ3W","created_at":"2026-07-05T04:16:55.784558+00:00"},{"alias_kind":"pith_short_16","alias_value":"T2UI65V2EJ3WFNB2","created_at":"2026-07-05T04:16:55.784558+00:00"},{"alias_kind":"pith_short_8","alias_value":"T2UI65V2","created_at":"2026-07-05T04:16:55.784558+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.01684","citing_title":"Reinforcement Learning for Machine Learning Engineering Agents","ref_index":50,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T2UI65V2EJ3WFNB24FQSSNZGWN","json":"https://pith.science/pith/T2UI65V2EJ3WFNB24FQSSNZGWN.json","graph_json":"https://pith.science/api/pith-number/T2UI65V2EJ3WFNB24FQSSNZGWN/graph.json","events_json":"https://pith.science/api/pith-number/T2UI65V2EJ3WFNB24FQSSNZGWN/events.json","paper":"https://pith.science/paper/T2UI65V2"},"agent_actions":{"view_html":"https://pith.science/pith/T2UI65V2EJ3WFNB24FQSSNZGWN","download_json":"https://pith.science/pith/T2UI65V2EJ3WFNB24FQSSNZGWN.json","view_paper":"https://pith.science/paper/T2UI65V2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.10198&json=true","fetch_graph":"https://pith.science/api/pith-number/T2UI65V2EJ3WFNB24FQSSNZGWN/graph.json","fetch_events":"https://pith.science/api/pith-number/T2UI65V2EJ3WFNB24FQSSNZGWN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T2UI65V2EJ3WFNB24FQSSNZGWN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T2UI65V2EJ3WFNB24FQSSNZGWN/action/storage_attestation","attest_author":"https://pith.science/pith/T2UI65V2EJ3WFNB24FQSSNZGWN/action/author_attestation","sign_citation":"https://pith.science/pith/T2UI65V2EJ3WFNB24FQSSNZGWN/action/citation_signature","submit_replication":"https://pith.science/pith/T2UI65V2EJ3WFNB24FQSSNZGWN/action/replication_record"}},"created_at":"2026-07-05T04:16:55.784558+00:00","updated_at":"2026-07-05T04:16:55.784558+00:00"}