{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:U5RHXJLEO6F7QK7YPKDDA6ST44","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":"97dfcf8e8ddc365a368bd9fad1d07800e325d64c96481665814d0c759c9032f2","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-14T16:44:33Z","title_canon_sha256":"914e1499c21725a80984b782d3c75adc5d98467022785f631a79b09279f804a3"},"schema_version":"1.0","source":{"id":"2311.08300","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.08300","created_at":"2026-07-05T07:12:43Z"},{"alias_kind":"arxiv_version","alias_value":"2311.08300v1","created_at":"2026-07-05T07:12:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.08300","created_at":"2026-07-05T07:12:43Z"},{"alias_kind":"pith_short_12","alias_value":"U5RHXJLEO6F7","created_at":"2026-07-05T07:12:43Z"},{"alias_kind":"pith_short_16","alias_value":"U5RHXJLEO6F7QK7Y","created_at":"2026-07-05T07:12:43Z"},{"alias_kind":"pith_short_8","alias_value":"U5RHXJLE","created_at":"2026-07-05T07:12:43Z"}],"graph_snapshots":[{"event_id":"sha256:7c43ed41d79afe1368f97f7e936830b840bec025c53289115f76510eab41c43b","target":"graph","created_at":"2026-07-05T07:12:43Z","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/2311.08300/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Task-oriented dialogue (TOD) systems aim to achieve specific goals through interactive dialogue. Such tasks usually involve following specific workflows, i.e. executing a sequence of actions in a particular order. While prior work has focused on supervised learning methods to condition on past actions, they do not explicitly optimize for compliance to a desired workflow. In this paper, we propose a novel framework based on reinforcement learning (RL) to generate dialogue responses that are aligned with a given workflow. Our framework consists of ComplianceScorer, a metric designed to evaluate ","authors_text":"Do June Min, Paloma Sodhi, Ramya Ramakrishnan","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-14T16:44:33Z","title":"Workflow-Guided Response Generation for Task-Oriented Dialogue"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.08300","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:d5e128b2690882e1b064560bdfd35ed703e1f7b82aa863192b323f60e3b433a2","target":"record","created_at":"2026-07-05T07:12:43Z","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":"97dfcf8e8ddc365a368bd9fad1d07800e325d64c96481665814d0c759c9032f2","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-14T16:44:33Z","title_canon_sha256":"914e1499c21725a80984b782d3c75adc5d98467022785f631a79b09279f804a3"},"schema_version":"1.0","source":{"id":"2311.08300","kind":"arxiv","version":1}},"canonical_sha256":"a7627ba564778bf82bf87a86307a53e70b64abf8c0513e96a745a4d556d8dd2a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a7627ba564778bf82bf87a86307a53e70b64abf8c0513e96a745a4d556d8dd2a","first_computed_at":"2026-07-05T07:12:43.420191Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:12:43.420191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0PqjTEypMabbq5nj8yQ75KdV5JtTEC4dMViOLn8ZSRCIA7gEOntJQZcj07puY7ka+dULNbvr5o72MQe0NjfQCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:12:43.420587Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.08300","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d5e128b2690882e1b064560bdfd35ed703e1f7b82aa863192b323f60e3b433a2","sha256:7c43ed41d79afe1368f97f7e936830b840bec025c53289115f76510eab41c43b"],"state_sha256":"2e459f74a548b248a7ce3bb8aaefbdbc7cf98200350d9c4e90f1ad0e1e09400f"}