{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:M4KCMUMQBVFHAVVJAWERJZRVGB","short_pith_number":"pith:M4KCMUMQ","schema_version":"1.0","canonical_sha256":"67142651900d4a7056a9058914e635307ac2df11b8cc75c4fff45e536ac6ce3b","source":{"kind":"arxiv","id":"2109.09597","version":1},"attestation_state":"computed","paper":{"title":"Two Approaches to Building Collaborative, Task-Oriented Dialog Agents through Self-Play","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.GT"],"primary_cat":"cs.CL","authors_text":"Ajay Nagesh, Arkady Arkhangorodsky, Kevin Knight, Maria Ryskina, Scot Fang, Victoria Knight","submitted_at":"2021-09-20T14:52:25Z","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."},"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":"2109.09597","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-20T14:52:25Z","cross_cats_sorted":["cs.AI","cs.GT"],"title_canon_sha256":"0a7c9f0723eab09ddb112b130ca75bf5b763a9be1a802827f833ad55fa15dbb5","abstract_canon_sha256":"e633346c93572a855ec62b3ef3724e6c23c3458ff5335616da649d124e358eff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:15:47.732027Z","signature_b64":"GXsNZ9CKH9TYQVE0ZW7FQdQOTTY9bX2COglAaEUNIbnp3N9S2MQksMiAd7DB9XCFmrlImw01t5ntYCYoGTe8Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67142651900d4a7056a9058914e635307ac2df11b8cc75c4fff45e536ac6ce3b","last_reissued_at":"2026-07-05T03:15:47.731445Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:15:47.731445Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Two Approaches to Building Collaborative, Task-Oriented Dialog Agents through Self-Play","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.GT"],"primary_cat":"cs.CL","authors_text":"Ajay Nagesh, Arkady Arkhangorodsky, Kevin Knight, Maria Ryskina, Scot Fang, Victoria Knight","submitted_at":"2021-09-20T14:52:25Z","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."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.09597","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2109.09597/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":"2109.09597","created_at":"2026-07-05T03:15:47.731514+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.09597v1","created_at":"2026-07-05T03:15:47.731514+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.09597","created_at":"2026-07-05T03:15:47.731514+00:00"},{"alias_kind":"pith_short_12","alias_value":"M4KCMUMQBVFH","created_at":"2026-07-05T03:15:47.731514+00:00"},{"alias_kind":"pith_short_16","alias_value":"M4KCMUMQBVFHAVVJ","created_at":"2026-07-05T03:15:47.731514+00:00"},{"alias_kind":"pith_short_8","alias_value":"M4KCMUMQ","created_at":"2026-07-05T03:15:47.731514+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.06856","citing_title":"Benchmarked Yet Not Measured -- Generative AI Should be Evaluated Against Real-World Utility","ref_index":222,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06856","citing_title":"Benchmarked Yet Not Measured -- Generative AI Should be Evaluated Against Real-World Utility","ref_index":222,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M4KCMUMQBVFHAVVJAWERJZRVGB","json":"https://pith.science/pith/M4KCMUMQBVFHAVVJAWERJZRVGB.json","graph_json":"https://pith.science/api/pith-number/M4KCMUMQBVFHAVVJAWERJZRVGB/graph.json","events_json":"https://pith.science/api/pith-number/M4KCMUMQBVFHAVVJAWERJZRVGB/events.json","paper":"https://pith.science/paper/M4KCMUMQ"},"agent_actions":{"view_html":"https://pith.science/pith/M4KCMUMQBVFHAVVJAWERJZRVGB","download_json":"https://pith.science/pith/M4KCMUMQBVFHAVVJAWERJZRVGB.json","view_paper":"https://pith.science/paper/M4KCMUMQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.09597&json=true","fetch_graph":"https://pith.science/api/pith-number/M4KCMUMQBVFHAVVJAWERJZRVGB/graph.json","fetch_events":"https://pith.science/api/pith-number/M4KCMUMQBVFHAVVJAWERJZRVGB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M4KCMUMQBVFHAVVJAWERJZRVGB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M4KCMUMQBVFHAVVJAWERJZRVGB/action/storage_attestation","attest_author":"https://pith.science/pith/M4KCMUMQBVFHAVVJAWERJZRVGB/action/author_attestation","sign_citation":"https://pith.science/pith/M4KCMUMQBVFHAVVJAWERJZRVGB/action/citation_signature","submit_replication":"https://pith.science/pith/M4KCMUMQBVFHAVVJAWERJZRVGB/action/replication_record"}},"created_at":"2026-07-05T03:15:47.731514+00:00","updated_at":"2026-07-05T03:15:47.731514+00:00"}