{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:M4KCMUMQBVFHAVVJAWERJZRVGB","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":"e633346c93572a855ec62b3ef3724e6c23c3458ff5335616da649d124e358eff","cross_cats_sorted":["cs.AI","cs.GT"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-20T14:52:25Z","title_canon_sha256":"0a7c9f0723eab09ddb112b130ca75bf5b763a9be1a802827f833ad55fa15dbb5"},"schema_version":"1.0","source":{"id":"2109.09597","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.09597","created_at":"2026-07-05T03:15:47Z"},{"alias_kind":"arxiv_version","alias_value":"2109.09597v1","created_at":"2026-07-05T03:15:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.09597","created_at":"2026-07-05T03:15:47Z"},{"alias_kind":"pith_short_12","alias_value":"M4KCMUMQBVFH","created_at":"2026-07-05T03:15:47Z"},{"alias_kind":"pith_short_16","alias_value":"M4KCMUMQBVFHAVVJ","created_at":"2026-07-05T03:15:47Z"},{"alias_kind":"pith_short_8","alias_value":"M4KCMUMQ","created_at":"2026-07-05T03:15:47Z"}],"graph_snapshots":[{"event_id":"sha256:6c0eb67df60d27a8cdee445c31faf4343f0563dd6cef480514bf3df8f35d5325","target":"graph","created_at":"2026-07-05T03:15:47Z","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/2109.09597/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Task-oriented dialog systems are often trained on human/human dialogs, such as collected from Wizard-of-Oz interfaces. However, human/human corpora are frequently too small for supervised training to be effective. This paper investigates two approaches to training agent-bots and user-bots through self-play, in which they autonomously explore an API environment, discovering communication strategies that enable them to solve the task. We give empirical results for both reinforcement learning and game-theoretic equilibrium finding.","authors_text":"Ajay Nagesh, Arkady Arkhangorodsky, Kevin Knight, Maria Ryskina, Scot Fang, Victoria Knight","cross_cats":["cs.AI","cs.GT"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-20T14:52:25Z","title":"Two Approaches to Building Collaborative, Task-Oriented Dialog Agents through Self-Play"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.09597","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":"sha256:21fdba53de71c2613a43fecca951e0474e2e96e8e48b4f05f0b61a8dada39d6c","target":"record","created_at":"2026-07-05T03:15:47Z","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":"e633346c93572a855ec62b3ef3724e6c23c3458ff5335616da649d124e358eff","cross_cats_sorted":["cs.AI","cs.GT"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-20T14:52:25Z","title_canon_sha256":"0a7c9f0723eab09ddb112b130ca75bf5b763a9be1a802827f833ad55fa15dbb5"},"schema_version":"1.0","source":{"id":"2109.09597","kind":"arxiv","version":1}},"canonical_sha256":"67142651900d4a7056a9058914e635307ac2df11b8cc75c4fff45e536ac6ce3b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"67142651900d4a7056a9058914e635307ac2df11b8cc75c4fff45e536ac6ce3b","first_computed_at":"2026-07-05T03:15:47.731445Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:15:47.731445Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GXsNZ9CKH9TYQVE0ZW7FQdQOTTY9bX2COglAaEUNIbnp3N9S2MQksMiAd7DB9XCFmrlImw01t5ntYCYoGTe8Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T03:15:47.732027Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.09597","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:21fdba53de71c2613a43fecca951e0474e2e96e8e48b4f05f0b61a8dada39d6c","sha256:6c0eb67df60d27a8cdee445c31faf4343f0563dd6cef480514bf3df8f35d5325"],"state_sha256":"a0caeade04d47ba2e177158eb17c4cd53e3fda037b5d4705a3dc7febecbdbd07"}