{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:TRGHR2X7JQGE2VMI4ESZ45ZYT6","short_pith_number":"pith:TRGHR2X7","canonical_record":{"source":{"id":"1804.07855","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-20T23:06:44Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"967e515ffe3d0c9c0d488a0275d075b90ff241f7c5ecb088a9e2cfb14b165698","abstract_canon_sha256":"5ee7c3180dbe0b2b38df4fe8ae0109b9156f3c5c1a203dba9950c271aa0609c0"},"schema_version":"1.0"},"canonical_sha256":"9c4c78eaff4c0c4d5588e1259e77389f9f97b2116fd0bcad594979514c159169","source":{"kind":"arxiv","id":"1804.07855","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.07855","created_at":"2026-05-18T00:05:05Z"},{"alias_kind":"arxiv_version","alias_value":"1804.07855v3","created_at":"2026-05-18T00:05:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.07855","created_at":"2026-05-18T00:05:05Z"},{"alias_kind":"pith_short_12","alias_value":"TRGHR2X7JQGE","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"TRGHR2X7JQGE2VMI","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"TRGHR2X7","created_at":"2026-05-18T12:32:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:TRGHR2X7JQGE2VMI4ESZ45ZYT6","target":"record","payload":{"canonical_record":{"source":{"id":"1804.07855","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-20T23:06:44Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"967e515ffe3d0c9c0d488a0275d075b90ff241f7c5ecb088a9e2cfb14b165698","abstract_canon_sha256":"5ee7c3180dbe0b2b38df4fe8ae0109b9156f3c5c1a203dba9950c271aa0609c0"},"schema_version":"1.0"},"canonical_sha256":"9c4c78eaff4c0c4d5588e1259e77389f9f97b2116fd0bcad594979514c159169","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:05:05.017086Z","signature_b64":"3M8/q+jufnsxo5vCmGNn/PvlV7046OOrz72euRpEXZQID6DJCoCS1jbjnrLMP8batLKq2u+Y4I6K2xYR1SLKBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c4c78eaff4c0c4d5588e1259e77389f9f97b2116fd0bcad594979514c159169","last_reissued_at":"2026-05-18T00:05:05.016157Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:05:05.016157Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1804.07855","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:05:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"znZVcZutUFSqAwAzhARP7cYkFWt1g1LCESrFM4zXRqVDqpvl/yn1Kem8t2ZtdiHdNoyUzbTgoKOodp6QUWPVCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T15:33:57.129997Z"},"content_sha256":"537901d1182eef64c7262a30814aeca3cf02cde1746eaae519bf0dbb948e008d","schema_version":"1.0","event_id":"sha256:537901d1182eef64c7262a30814aeca3cf02cde1746eaae519bf0dbb948e008d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:TRGHR2X7JQGE2VMI4ESZ45ZYT6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Subgoal Discovery for Hierarchical Dialogue Policy Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chong Wang, Da Tang, Jianfeng Gao, Lihong Li, Tony Jebara, Xiujun Li","submitted_at":"2018-04-20T23:06:44Z","abstract_excerpt":"Developing agents to engage in complex goal-oriented dialogues is challenging partly because the main learning signals are very sparse in long conversations. In this paper, we propose a divide-and-conquer approach that discovers and exploits the hidden structure of the task to enable efficient policy learning. First, given successful example dialogues, we propose the Subgoal Discovery Network (SDN) to divide a complex goal-oriented task into a set of simpler subgoals in an unsupervised fashion. We then use these subgoals to learn a multi-level policy by hierarchical reinforcement learning. We "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.07855","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2026-05-18T00:05:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oZHunQEHfqsI7WlwgyZMnYzzRjlN6w2nXgUWtw3czbWA+9tgUejUKbsYdiUT9hcMV2O2hlanindPTXvVlhKNDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T15:33:57.130346Z"},"content_sha256":"8a3e4e8f7af87ae4e8aac7d24fe7448cfef67fb75f768b6508a448b1a4056cd3","schema_version":"1.0","event_id":"sha256:8a3e4e8f7af87ae4e8aac7d24fe7448cfef67fb75f768b6508a448b1a4056cd3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TRGHR2X7JQGE2VMI4ESZ45ZYT6/bundle.json","state_url":"https://pith.science/pith/TRGHR2X7JQGE2VMI4ESZ45ZYT6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TRGHR2X7JQGE2VMI4ESZ45ZYT6/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":"2026-06-01T15:33:57Z","links":{"resolver":"https://pith.science/pith/TRGHR2X7JQGE2VMI4ESZ45ZYT6","bundle":"https://pith.science/pith/TRGHR2X7JQGE2VMI4ESZ45ZYT6/bundle.json","state":"https://pith.science/pith/TRGHR2X7JQGE2VMI4ESZ45ZYT6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TRGHR2X7JQGE2VMI4ESZ45ZYT6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:TRGHR2X7JQGE2VMI4ESZ45ZYT6","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":"5ee7c3180dbe0b2b38df4fe8ae0109b9156f3c5c1a203dba9950c271aa0609c0","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-20T23:06:44Z","title_canon_sha256":"967e515ffe3d0c9c0d488a0275d075b90ff241f7c5ecb088a9e2cfb14b165698"},"schema_version":"1.0","source":{"id":"1804.07855","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.07855","created_at":"2026-05-18T00:05:05Z"},{"alias_kind":"arxiv_version","alias_value":"1804.07855v3","created_at":"2026-05-18T00:05:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.07855","created_at":"2026-05-18T00:05:05Z"},{"alias_kind":"pith_short_12","alias_value":"TRGHR2X7JQGE","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"TRGHR2X7JQGE2VMI","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"TRGHR2X7","created_at":"2026-05-18T12:32:56Z"}],"graph_snapshots":[{"event_id":"sha256:8a3e4e8f7af87ae4e8aac7d24fe7448cfef67fb75f768b6508a448b1a4056cd3","target":"graph","created_at":"2026-05-18T00:05:05Z","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"},"paper":{"abstract_excerpt":"Developing agents to engage in complex goal-oriented dialogues is challenging partly because the main learning signals are very sparse in long conversations. In this paper, we propose a divide-and-conquer approach that discovers and exploits the hidden structure of the task to enable efficient policy learning. First, given successful example dialogues, we propose the Subgoal Discovery Network (SDN) to divide a complex goal-oriented task into a set of simpler subgoals in an unsupervised fashion. We then use these subgoals to learn a multi-level policy by hierarchical reinforcement learning. We ","authors_text":"Chong Wang, Da Tang, Jianfeng Gao, Lihong Li, Tony Jebara, Xiujun Li","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-20T23:06:44Z","title":"Subgoal Discovery for Hierarchical Dialogue Policy Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.07855","kind":"arxiv","version":3},"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":"sha256:537901d1182eef64c7262a30814aeca3cf02cde1746eaae519bf0dbb948e008d","target":"record","created_at":"2026-05-18T00:05:05Z","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":"5ee7c3180dbe0b2b38df4fe8ae0109b9156f3c5c1a203dba9950c271aa0609c0","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-20T23:06:44Z","title_canon_sha256":"967e515ffe3d0c9c0d488a0275d075b90ff241f7c5ecb088a9e2cfb14b165698"},"schema_version":"1.0","source":{"id":"1804.07855","kind":"arxiv","version":3}},"canonical_sha256":"9c4c78eaff4c0c4d5588e1259e77389f9f97b2116fd0bcad594979514c159169","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9c4c78eaff4c0c4d5588e1259e77389f9f97b2116fd0bcad594979514c159169","first_computed_at":"2026-05-18T00:05:05.016157Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:05:05.016157Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3M8/q+jufnsxo5vCmGNn/PvlV7046OOrz72euRpEXZQID6DJCoCS1jbjnrLMP8batLKq2u+Y4I6K2xYR1SLKBw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:05:05.017086Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.07855","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:537901d1182eef64c7262a30814aeca3cf02cde1746eaae519bf0dbb948e008d","sha256:8a3e4e8f7af87ae4e8aac7d24fe7448cfef67fb75f768b6508a448b1a4056cd3"],"state_sha256":"13bd630c2bad11ae3e3ed7f16783c8e66b931a7848bfd18520f1b07a583c52c2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7qHbmfJKhbFEK73nrF4599BZFsxtHwZdFLvAepidOKSLasyXxOvTQrDciShTmpqYgIGJeUL3ISlR9laea/ADDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T15:33:57.132225Z","bundle_sha256":"b4416293a9e729f349180b19509b34e18424416b95f561b6453ddc105a8a702a"}}