{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7D5MU4UCS7QZZJOC4Z7RMHY5J6","short_pith_number":"pith:7D5MU4UC","schema_version":"1.0","canonical_sha256":"f8faca728297e19ca5c2e67f161f1d4f8ea5da2261f321da5702fbf61055df85","source":{"kind":"arxiv","id":"2305.13660","version":2},"attestation_state":"computed","paper":{"title":"Prompt-Based Monte-Carlo Tree Search for Goal-Oriented Dialogue Policy Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Maximillian Chen, Xiao Yu, Zhou Yu","submitted_at":"2023-05-23T04:07:03Z","abstract_excerpt":"Planning for goal-oriented dialogue often requires simulating future dialogue interactions and estimating task progress. Many approaches thus consider training neural networks to perform look-ahead search algorithms such as A* search and Monte Carlo Tree Search (MCTS). However, this training often requires abundant annotated data, which creates challenges when faced with noisy annotations or low-resource settings. We introduce GDP-Zero, an approach using Open-Loop MCTS to perform goal-oriented dialogue policy planning without any model training. GDP-Zero prompts a large language model to act a"},"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":"2305.13660","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T04:07:03Z","cross_cats_sorted":[],"title_canon_sha256":"a70392e7c93d9012d4dd7296db04fdbbed190b77e0a630feae5cada7e4a8897a","abstract_canon_sha256":"c633c0fd09da1902b0e424312782d77e3b9e1430241f60ecbf3765b472cc02f4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:02:50.426902Z","signature_b64":"s4kFNGUECIRxMafaQpocdj0V4zZ68znl/laZd7tYVqFA1hC/U9bBLWfbenpUGHMGYiIbmAsgm88NwdGMbimsCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8faca728297e19ca5c2e67f161f1d4f8ea5da2261f321da5702fbf61055df85","last_reissued_at":"2026-07-05T07:02:50.426293Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:02:50.426293Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prompt-Based Monte-Carlo Tree Search for Goal-Oriented Dialogue Policy Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Maximillian Chen, Xiao Yu, Zhou Yu","submitted_at":"2023-05-23T04:07:03Z","abstract_excerpt":"Planning for goal-oriented dialogue often requires simulating future dialogue interactions and estimating task progress. Many approaches thus consider training neural networks to perform look-ahead search algorithms such as A* search and Monte Carlo Tree Search (MCTS). However, this training often requires abundant annotated data, which creates challenges when faced with noisy annotations or low-resource settings. We introduce GDP-Zero, an approach using Open-Loop MCTS to perform goal-oriented dialogue policy planning without any model training. GDP-Zero prompts a large language model to act a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13660","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/2305.13660/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":"2305.13660","created_at":"2026-07-05T07:02:50.426365+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.13660v2","created_at":"2026-07-05T07:02:50.426365+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13660","created_at":"2026-07-05T07:02:50.426365+00:00"},{"alias_kind":"pith_short_12","alias_value":"7D5MU4UCS7QZ","created_at":"2026-07-05T07:02:50.426365+00:00"},{"alias_kind":"pith_short_16","alias_value":"7D5MU4UCS7QZZJOC","created_at":"2026-07-05T07:02:50.426365+00:00"},{"alias_kind":"pith_short_8","alias_value":"7D5MU4UC","created_at":"2026-07-05T07:02:50.426365+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01182","citing_title":"CA-BED: Conversation-Aware Bayesian Experimental Design","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2601.12538","citing_title":"Agentic Reasoning for Large Language Models","ref_index":115,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23345","citing_title":"Bridging Reasoning and Action: Hybrid LLM-RL Framework for Efficient Cross-Domain Task-Oriented Dialogue","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18539","citing_title":"Transition-Matrix Regularization for Next Dialogue Act Prediction in Counselling Conversations","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7D5MU4UCS7QZZJOC4Z7RMHY5J6","json":"https://pith.science/pith/7D5MU4UCS7QZZJOC4Z7RMHY5J6.json","graph_json":"https://pith.science/api/pith-number/7D5MU4UCS7QZZJOC4Z7RMHY5J6/graph.json","events_json":"https://pith.science/api/pith-number/7D5MU4UCS7QZZJOC4Z7RMHY5J6/events.json","paper":"https://pith.science/paper/7D5MU4UC"},"agent_actions":{"view_html":"https://pith.science/pith/7D5MU4UCS7QZZJOC4Z7RMHY5J6","download_json":"https://pith.science/pith/7D5MU4UCS7QZZJOC4Z7RMHY5J6.json","view_paper":"https://pith.science/paper/7D5MU4UC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.13660&json=true","fetch_graph":"https://pith.science/api/pith-number/7D5MU4UCS7QZZJOC4Z7RMHY5J6/graph.json","fetch_events":"https://pith.science/api/pith-number/7D5MU4UCS7QZZJOC4Z7RMHY5J6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7D5MU4UCS7QZZJOC4Z7RMHY5J6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7D5MU4UCS7QZZJOC4Z7RMHY5J6/action/storage_attestation","attest_author":"https://pith.science/pith/7D5MU4UCS7QZZJOC4Z7RMHY5J6/action/author_attestation","sign_citation":"https://pith.science/pith/7D5MU4UCS7QZZJOC4Z7RMHY5J6/action/citation_signature","submit_replication":"https://pith.science/pith/7D5MU4UCS7QZZJOC4Z7RMHY5J6/action/replication_record"}},"created_at":"2026-07-05T07:02:50.426365+00:00","updated_at":"2026-07-05T07:02:50.426365+00:00"}