{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:T2UI65V2EJ3WFNB24FQSSNZGWN","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":"a51a3e62324818995c6e81959e840fd81db1787e14981c024452c55fad687ab2","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-18T17:23:11Z","title_canon_sha256":"80b7bd64656b6783e245b76f33382f112d8df9d98102b4654f596324dcc23eba"},"schema_version":"1.0","source":{"id":"2204.10198","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.10198","created_at":"2026-07-05T04:16:55Z"},{"alias_kind":"arxiv_version","alias_value":"2204.10198v2","created_at":"2026-07-05T04:16:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.10198","created_at":"2026-07-05T04:16:55Z"},{"alias_kind":"pith_short_12","alias_value":"T2UI65V2EJ3W","created_at":"2026-07-05T04:16:55Z"},{"alias_kind":"pith_short_16","alias_value":"T2UI65V2EJ3WFNB2","created_at":"2026-07-05T04:16:55Z"},{"alias_kind":"pith_short_8","alias_value":"T2UI65V2","created_at":"2026-07-05T04:16:55Z"}],"graph_snapshots":[{"event_id":"sha256:cf2d601b21da6d1f338bc813c270f090b65d81022acdd687ea8a81cf3bdcd22f","target":"graph","created_at":"2026-07-05T04:16:55Z","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/2204.10198/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Charlie Snell, Justin Fu, Mengjiao Yang, Sergey Levine, Yi Su","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-18T17:23:11Z","title":"Context-Aware Language Modeling for Goal-Oriented Dialogue Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.10198","kind":"arxiv","version":2},"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":"sha256:15220bf4829149dd339f33143fa8a2a4f8ac702d93f611ff67e863b8fa7dcc01","target":"record","created_at":"2026-07-05T04:16:55Z","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":"a51a3e62324818995c6e81959e840fd81db1787e14981c024452c55fad687ab2","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-18T17:23:11Z","title_canon_sha256":"80b7bd64656b6783e245b76f33382f112d8df9d98102b4654f596324dcc23eba"},"schema_version":"1.0","source":{"id":"2204.10198","kind":"arxiv","version":2}},"canonical_sha256":"9ea88f76ba227762b43ae161293726b34d4f7c94303c5f171e0ab463f86da9d9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9ea88f76ba227762b43ae161293726b34d4f7c94303c5f171e0ab463f86da9d9","first_computed_at":"2026-07-05T04:16:55.784502Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:16:55.784502Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9iE2sRwjziu2oAEI74SOGDAClgKazbZRjhLIqTybNptEHZbreosFQkUnLrPH+czwHhDj4HXtZeWvHhZSXOYDBA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:16:55.785021Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.10198","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:15220bf4829149dd339f33143fa8a2a4f8ac702d93f611ff67e863b8fa7dcc01","sha256:cf2d601b21da6d1f338bc813c270f090b65d81022acdd687ea8a81cf3bdcd22f"],"state_sha256":"a3ab9e15b8ae29dfd7645593fa26c695c915575511ea391a9f829d62206e337a"}