{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:7UNWM7J5EVW5PTJSTEIHMNNTBY","short_pith_number":"pith:7UNWM7J5","schema_version":"1.0","canonical_sha256":"fd1b667d3d256dd7cd3299107635b30e1dcdd43836ae2fb973e33289fbf95ac7","source":{"kind":"arxiv","id":"2009.10355","version":1},"attestation_state":"computed","paper":{"title":"Structured Hierarchical Dialogue Policy with Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kai Yu, Lu Chen, Xiaoyuan Liu, Zhi Chen","submitted_at":"2020-09-22T07:23:02Z","abstract_excerpt":"Dialogue policy training for composite tasks, such as restaurant reservation in multiple places, is a practically important and challenging problem. Recently, hierarchical deep reinforcement learning (HDRL) methods have achieved good performance in composite tasks. However, in vanilla HDRL, both top-level and low-level policies are all represented by multi-layer perceptrons (MLPs) which take the concatenation of all observations from the environment as the input for predicting actions. Thus, traditional HDRL approach often suffers from low sampling efficiency and poor transferability. In this "},"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":"2009.10355","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-22T07:23:02Z","cross_cats_sorted":[],"title_canon_sha256":"430ec0f0b289ecffa895a02ab913a319d46e3ca034b181689081fc9eed00602a","abstract_canon_sha256":"cb70fcbc732fe8bdc17f7ccc9b8821da8a41cbb1824826ab3e0944e9ffae98b0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:37:18.563351Z","signature_b64":"ChD9GMJD6kFmETNAl7OEI1G+Xc7Q2Ayng40X8jPUAnNFwFEaz2AN8sqCDZ4PXsG+UC4D8XsVGp49VjLZgP+KDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd1b667d3d256dd7cd3299107635b30e1dcdd43836ae2fb973e33289fbf95ac7","last_reissued_at":"2026-07-05T01:37:18.562981Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:37:18.562981Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Structured Hierarchical Dialogue Policy with Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kai Yu, Lu Chen, Xiaoyuan Liu, Zhi Chen","submitted_at":"2020-09-22T07:23:02Z","abstract_excerpt":"Dialogue policy training for composite tasks, such as restaurant reservation in multiple places, is a practically important and challenging problem. Recently, hierarchical deep reinforcement learning (HDRL) methods have achieved good performance in composite tasks. However, in vanilla HDRL, both top-level and low-level policies are all represented by multi-layer perceptrons (MLPs) which take the concatenation of all observations from the environment as the input for predicting actions. Thus, traditional HDRL approach often suffers from low sampling efficiency and poor transferability. In this "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.10355","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/2009.10355/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":"2009.10355","created_at":"2026-07-05T01:37:18.563043+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.10355v1","created_at":"2026-07-05T01:37:18.563043+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.10355","created_at":"2026-07-05T01:37:18.563043+00:00"},{"alias_kind":"pith_short_12","alias_value":"7UNWM7J5EVW5","created_at":"2026-07-05T01:37:18.563043+00:00"},{"alias_kind":"pith_short_16","alias_value":"7UNWM7J5EVW5PTJS","created_at":"2026-07-05T01:37:18.563043+00:00"},{"alias_kind":"pith_short_8","alias_value":"7UNWM7J5","created_at":"2026-07-05T01:37:18.563043+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7UNWM7J5EVW5PTJSTEIHMNNTBY","json":"https://pith.science/pith/7UNWM7J5EVW5PTJSTEIHMNNTBY.json","graph_json":"https://pith.science/api/pith-number/7UNWM7J5EVW5PTJSTEIHMNNTBY/graph.json","events_json":"https://pith.science/api/pith-number/7UNWM7J5EVW5PTJSTEIHMNNTBY/events.json","paper":"https://pith.science/paper/7UNWM7J5"},"agent_actions":{"view_html":"https://pith.science/pith/7UNWM7J5EVW5PTJSTEIHMNNTBY","download_json":"https://pith.science/pith/7UNWM7J5EVW5PTJSTEIHMNNTBY.json","view_paper":"https://pith.science/paper/7UNWM7J5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.10355&json=true","fetch_graph":"https://pith.science/api/pith-number/7UNWM7J5EVW5PTJSTEIHMNNTBY/graph.json","fetch_events":"https://pith.science/api/pith-number/7UNWM7J5EVW5PTJSTEIHMNNTBY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7UNWM7J5EVW5PTJSTEIHMNNTBY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7UNWM7J5EVW5PTJSTEIHMNNTBY/action/storage_attestation","attest_author":"https://pith.science/pith/7UNWM7J5EVW5PTJSTEIHMNNTBY/action/author_attestation","sign_citation":"https://pith.science/pith/7UNWM7J5EVW5PTJSTEIHMNNTBY/action/citation_signature","submit_replication":"https://pith.science/pith/7UNWM7J5EVW5PTJSTEIHMNNTBY/action/replication_record"}},"created_at":"2026-07-05T01:37:18.563043+00:00","updated_at":"2026-07-05T01:37:18.563043+00:00"}