{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:7UNWM7J5EVW5PTJSTEIHMNNTBY","short_pith_number":"pith:7UNWM7J5","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"},"canonical_sha256":"fd1b667d3d256dd7cd3299107635b30e1dcdd43836ae2fb973e33289fbf95ac7","source":{"kind":"arxiv","id":"2009.10355","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.10355","created_at":"2026-07-05T01:37:18Z"},{"alias_kind":"arxiv_version","alias_value":"2009.10355v1","created_at":"2026-07-05T01:37:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.10355","created_at":"2026-07-05T01:37:18Z"},{"alias_kind":"pith_short_12","alias_value":"7UNWM7J5EVW5","created_at":"2026-07-05T01:37:18Z"},{"alias_kind":"pith_short_16","alias_value":"7UNWM7J5EVW5PTJS","created_at":"2026-07-05T01:37:18Z"},{"alias_kind":"pith_short_8","alias_value":"7UNWM7J5","created_at":"2026-07-05T01:37:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:7UNWM7J5EVW5PTJSTEIHMNNTBY","target":"record","payload":{"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"},"canonical_sha256":"fd1b667d3d256dd7cd3299107635b30e1dcdd43836ae2fb973e33289fbf95ac7","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"},"source_kind":"arxiv","source_id":"2009.10355","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:37:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5yLjZcpVmmuSRiYD8UVunEacJf2chfOTMcbt9c/nYNbLHspjYo4MK4gElY9kXkouJ4+IgknlJZkYs+d2tYcoCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T12:28:23.499234Z"},"content_sha256":"8c9379e97417bbd3f588d3210ef55480a9b143cdcc6799db768fba64bd64a874","schema_version":"1.0","event_id":"sha256:8c9379e97417bbd3f588d3210ef55480a9b143cdcc6799db768fba64bd64a874"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:7UNWM7J5EVW5PTJSTEIHMNNTBY","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:37:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dvUC24Kw2GgzKNjmderVwI3CsUwKcx/sqQZERBNQ5WOxIv4pD5DR3L/D4kCQc4m1a2zKVwx+nOolUFCxhlIPBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T12:28:23.499629Z"},"content_sha256":"a6cbbd4bdc758c981c8b08f2540b42508f4f3af2931f627d8ddd88ffabd2cea6","schema_version":"1.0","event_id":"sha256:a6cbbd4bdc758c981c8b08f2540b42508f4f3af2931f627d8ddd88ffabd2cea6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7UNWM7J5EVW5PTJSTEIHMNNTBY/bundle.json","state_url":"https://pith.science/pith/7UNWM7J5EVW5PTJSTEIHMNNTBY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7UNWM7J5EVW5PTJSTEIHMNNTBY/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-06T12:28:23Z","links":{"resolver":"https://pith.science/pith/7UNWM7J5EVW5PTJSTEIHMNNTBY","bundle":"https://pith.science/pith/7UNWM7J5EVW5PTJSTEIHMNNTBY/bundle.json","state":"https://pith.science/pith/7UNWM7J5EVW5PTJSTEIHMNNTBY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7UNWM7J5EVW5PTJSTEIHMNNTBY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:7UNWM7J5EVW5PTJSTEIHMNNTBY","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":"cb70fcbc732fe8bdc17f7ccc9b8821da8a41cbb1824826ab3e0944e9ffae98b0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-22T07:23:02Z","title_canon_sha256":"430ec0f0b289ecffa895a02ab913a319d46e3ca034b181689081fc9eed00602a"},"schema_version":"1.0","source":{"id":"2009.10355","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.10355","created_at":"2026-07-05T01:37:18Z"},{"alias_kind":"arxiv_version","alias_value":"2009.10355v1","created_at":"2026-07-05T01:37:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.10355","created_at":"2026-07-05T01:37:18Z"},{"alias_kind":"pith_short_12","alias_value":"7UNWM7J5EVW5","created_at":"2026-07-05T01:37:18Z"},{"alias_kind":"pith_short_16","alias_value":"7UNWM7J5EVW5PTJS","created_at":"2026-07-05T01:37:18Z"},{"alias_kind":"pith_short_8","alias_value":"7UNWM7J5","created_at":"2026-07-05T01:37:18Z"}],"graph_snapshots":[{"event_id":"sha256:a6cbbd4bdc758c981c8b08f2540b42508f4f3af2931f627d8ddd88ffabd2cea6","target":"graph","created_at":"2026-07-05T01:37:18Z","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/2009.10355/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Kai Yu, Lu Chen, Xiaoyuan Liu, Zhi Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-22T07:23:02Z","title":"Structured Hierarchical Dialogue Policy with Graph Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.10355","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":"sha256:8c9379e97417bbd3f588d3210ef55480a9b143cdcc6799db768fba64bd64a874","target":"record","created_at":"2026-07-05T01:37:18Z","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":"cb70fcbc732fe8bdc17f7ccc9b8821da8a41cbb1824826ab3e0944e9ffae98b0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-22T07:23:02Z","title_canon_sha256":"430ec0f0b289ecffa895a02ab913a319d46e3ca034b181689081fc9eed00602a"},"schema_version":"1.0","source":{"id":"2009.10355","kind":"arxiv","version":1}},"canonical_sha256":"fd1b667d3d256dd7cd3299107635b30e1dcdd43836ae2fb973e33289fbf95ac7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fd1b667d3d256dd7cd3299107635b30e1dcdd43836ae2fb973e33289fbf95ac7","first_computed_at":"2026-07-05T01:37:18.562981Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:37:18.562981Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ChD9GMJD6kFmETNAl7OEI1G+Xc7Q2Ayng40X8jPUAnNFwFEaz2AN8sqCDZ4PXsG+UC4D8XsVGp49VjLZgP+KDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:37:18.563351Z","signed_message":"canonical_sha256_bytes"},"source_id":"2009.10355","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8c9379e97417bbd3f588d3210ef55480a9b143cdcc6799db768fba64bd64a874","sha256:a6cbbd4bdc758c981c8b08f2540b42508f4f3af2931f627d8ddd88ffabd2cea6"],"state_sha256":"6270a78522e5c2a1cead87baa60b72f606f9e17f893c00efa670e47b65d844cc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vSjVrSh8p+Che42Vk2PsfE9lcbmQ+2Gv/MOJjif7VU5tG21rfXH35WkQkX5Pz5d3yX4TmV1LNItd3HeU9gU1Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T12:28:23.501542Z","bundle_sha256":"add6e1c5680983eccd8dfa35700d6867d22756e83cf3e79167382e9eb375ff08"}}