{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:IUFXF2MN4L5MMQQVT2MYED7ETX","short_pith_number":"pith:IUFXF2MN","schema_version":"1.0","canonical_sha256":"450b72e98de2fac642159e99820fe49de69352e939366081dd90240d6d5abfb6","source":{"kind":"arxiv","id":"2005.00123","version":2},"attestation_state":"computed","paper":{"title":"Unsupervised Learning of KB Queries in Task-Oriented Dialogs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dinesh Raghu, Mausam, Nikhil Gupta","submitted_at":"2020-04-30T22:10:00Z","abstract_excerpt":"Task-oriented dialog (TOD) systems often need to formulate knowledge base (KB) queries corresponding to the user intent and use the query results to generate system responses. Existing approaches require dialog datasets to explicitly annotate these KB queries -- these annotations can be time consuming, and expensive. In response, we define the novel problems of predicting the KB query and training the dialog agent, without explicit KB query annotation. For query prediction, we propose a reinforcement learning (RL) baseline, which rewards the generation of those queries whose KB results cover t"},"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":"2005.00123","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-30T22:10:00Z","cross_cats_sorted":["cs.CL","stat.ML"],"title_canon_sha256":"991d451626ee0e27b1b7fe64f0a58fbbe3d357c25415241e75311134366d4891","abstract_canon_sha256":"6d1fe9176a6ad97136b0c422d21b5b2cdfa283918895162341e41831325c0def"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:45:47.772557Z","signature_b64":"CZOiioGinq1DZHWvgpfCo8KQNyCnKYDy2duRxmYAWxNS8SvXM5VPYfRugUy1PpFuThqHl3xrvH13E1JPkn5YCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"450b72e98de2fac642159e99820fe49de69352e939366081dd90240d6d5abfb6","last_reissued_at":"2026-07-05T02:45:47.772090Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:45:47.772090Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Learning of KB Queries in Task-Oriented Dialogs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dinesh Raghu, Mausam, Nikhil Gupta","submitted_at":"2020-04-30T22:10:00Z","abstract_excerpt":"Task-oriented dialog (TOD) systems often need to formulate knowledge base (KB) queries corresponding to the user intent and use the query results to generate system responses. Existing approaches require dialog datasets to explicitly annotate these KB queries -- these annotations can be time consuming, and expensive. In response, we define the novel problems of predicting the KB query and training the dialog agent, without explicit KB query annotation. For query prediction, we propose a reinforcement learning (RL) baseline, which rewards the generation of those queries whose KB results cover t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.00123","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/2005.00123/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":"2005.00123","created_at":"2026-07-05T02:45:47.772145+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.00123v2","created_at":"2026-07-05T02:45:47.772145+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.00123","created_at":"2026-07-05T02:45:47.772145+00:00"},{"alias_kind":"pith_short_12","alias_value":"IUFXF2MN4L5M","created_at":"2026-07-05T02:45:47.772145+00:00"},{"alias_kind":"pith_short_16","alias_value":"IUFXF2MN4L5MMQQV","created_at":"2026-07-05T02:45:47.772145+00:00"},{"alias_kind":"pith_short_8","alias_value":"IUFXF2MN","created_at":"2026-07-05T02:45:47.772145+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.06496","citing_title":"Med-GRIM: Enhanced Zero-Shot Medical VQA using prompt-embedded Multimodal Graph RAG","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IUFXF2MN4L5MMQQVT2MYED7ETX","json":"https://pith.science/pith/IUFXF2MN4L5MMQQVT2MYED7ETX.json","graph_json":"https://pith.science/api/pith-number/IUFXF2MN4L5MMQQVT2MYED7ETX/graph.json","events_json":"https://pith.science/api/pith-number/IUFXF2MN4L5MMQQVT2MYED7ETX/events.json","paper":"https://pith.science/paper/IUFXF2MN"},"agent_actions":{"view_html":"https://pith.science/pith/IUFXF2MN4L5MMQQVT2MYED7ETX","download_json":"https://pith.science/pith/IUFXF2MN4L5MMQQVT2MYED7ETX.json","view_paper":"https://pith.science/paper/IUFXF2MN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.00123&json=true","fetch_graph":"https://pith.science/api/pith-number/IUFXF2MN4L5MMQQVT2MYED7ETX/graph.json","fetch_events":"https://pith.science/api/pith-number/IUFXF2MN4L5MMQQVT2MYED7ETX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IUFXF2MN4L5MMQQVT2MYED7ETX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IUFXF2MN4L5MMQQVT2MYED7ETX/action/storage_attestation","attest_author":"https://pith.science/pith/IUFXF2MN4L5MMQQVT2MYED7ETX/action/author_attestation","sign_citation":"https://pith.science/pith/IUFXF2MN4L5MMQQVT2MYED7ETX/action/citation_signature","submit_replication":"https://pith.science/pith/IUFXF2MN4L5MMQQVT2MYED7ETX/action/replication_record"}},"created_at":"2026-07-05T02:45:47.772145+00:00","updated_at":"2026-07-05T02:45:47.772145+00:00"}