{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:LTXEND7SHZA7L2CVZGQWKXHQRK","short_pith_number":"pith:LTXEND7S","canonical_record":{"source":{"id":"2004.14254","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-04-29T15:02:41Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"0a11adf5dae90c07f92f9a4b24c52b33858c470667d41cf24585a33a470d546f","abstract_canon_sha256":"f0a557eacf10878ec70088045e4f27a4341d2e0b10ae324d27238a0c781d1c78"},"schema_version":"1.0"},"canonical_sha256":"5cee468ff23e41f5e855c9a1655cf08a84ac01ef5107cf8bec424b3dd52a135c","source":{"kind":"arxiv","id":"2004.14254","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.14254","created_at":"2026-07-05T07:09:41Z"},{"alias_kind":"arxiv_version","alias_value":"2004.14254v2","created_at":"2026-07-05T07:09:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.14254","created_at":"2026-07-05T07:09:41Z"},{"alias_kind":"pith_short_12","alias_value":"LTXEND7SHZA7","created_at":"2026-07-05T07:09:41Z"},{"alias_kind":"pith_short_16","alias_value":"LTXEND7SHZA7L2CV","created_at":"2026-07-05T07:09:41Z"},{"alias_kind":"pith_short_8","alias_value":"LTXEND7S","created_at":"2026-07-05T07:09:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:LTXEND7SHZA7L2CVZGQWKXHQRK","target":"record","payload":{"canonical_record":{"source":{"id":"2004.14254","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-04-29T15:02:41Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"0a11adf5dae90c07f92f9a4b24c52b33858c470667d41cf24585a33a470d546f","abstract_canon_sha256":"f0a557eacf10878ec70088045e4f27a4341d2e0b10ae324d27238a0c781d1c78"},"schema_version":"1.0"},"canonical_sha256":"5cee468ff23e41f5e855c9a1655cf08a84ac01ef5107cf8bec424b3dd52a135c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:09:41.146437Z","signature_b64":"0H3J1dV7WZSPG+IqmyEguItb3CJjGiS/9NPvkxCtJuR8swzuhEVAj5Yy3N/6sPwdqB+gi4RfBPuDLH12mVnuBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5cee468ff23e41f5e855c9a1655cf08a84ac01ef5107cf8bec424b3dd52a135c","last_reissued_at":"2026-07-05T07:09:41.145999Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:09:41.145999Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2004.14254","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:09:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ofP9hTGOWpCzBSP8fvC58R2A5rmh+JFQu9WoMQBkrpGCZ/vq0DV3PT75ruuQp+e5V8q/Xu4PX/WycK87E6DmAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T12:17:20.575748Z"},"content_sha256":"7bc5fa0dbed4cbfb0dafb744ae2df2bb1ab8aa8b924b9f70769717bf48a16eb6","schema_version":"1.0","event_id":"sha256:7bc5fa0dbed4cbfb0dafb744ae2df2bb1ab8aa8b924b9f70769717bf48a16eb6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:LTXEND7SHZA7L2CVZGQWKXHQRK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hierarchical Reinforcement Learning for Automatic Disease Diagnosis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Baolin Peng, Cheng Zhong, Jiajie Peng, Kangenbei Liao, Qianlong Liu, Wei Chen, Xuanjing Huang, Zhongyu Wei","submitted_at":"2020-04-29T15:02:41Z","abstract_excerpt":"Motivation: Disease diagnosis oriented dialogue system models the interactive consultation procedure as Markov Decision Process and reinforcement learning algorithms are used to solve the problem. Existing approaches usually employ a flat policy structure that treat all symptoms and diseases equally for action making. This strategy works well in the simple scenario when the action space is small, however, its efficiency will be challenged in the real environment. Inspired by the offline consultation process, we propose to integrate a hierarchical policy structure of two levels into the dialogu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.14254","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/2004.14254/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":"2026-07-05T07:09:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XGmZh+MMVQplGMn1c9fcIynDTNutY+yNZ5/oDVj+I9C4wqGpdB093ST+VqAePjG+/qMBlJHWOatmX5fPi++cDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T12:17:20.576717Z"},"content_sha256":"a2e979e0541647acdc140b305e6424dcc0a28d97c31b6843dec2952850db3ec8","schema_version":"1.0","event_id":"sha256:a2e979e0541647acdc140b305e6424dcc0a28d97c31b6843dec2952850db3ec8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LTXEND7SHZA7L2CVZGQWKXHQRK/bundle.json","state_url":"https://pith.science/pith/LTXEND7SHZA7L2CVZGQWKXHQRK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LTXEND7SHZA7L2CVZGQWKXHQRK/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":"2026-08-07T12:17:20Z","links":{"resolver":"https://pith.science/pith/LTXEND7SHZA7L2CVZGQWKXHQRK","bundle":"https://pith.science/pith/LTXEND7SHZA7L2CVZGQWKXHQRK/bundle.json","state":"https://pith.science/pith/LTXEND7SHZA7L2CVZGQWKXHQRK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LTXEND7SHZA7L2CVZGQWKXHQRK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:LTXEND7SHZA7L2CVZGQWKXHQRK","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":"f0a557eacf10878ec70088045e4f27a4341d2e0b10ae324d27238a0c781d1c78","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-04-29T15:02:41Z","title_canon_sha256":"0a11adf5dae90c07f92f9a4b24c52b33858c470667d41cf24585a33a470d546f"},"schema_version":"1.0","source":{"id":"2004.14254","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.14254","created_at":"2026-07-05T07:09:41Z"},{"alias_kind":"arxiv_version","alias_value":"2004.14254v2","created_at":"2026-07-05T07:09:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.14254","created_at":"2026-07-05T07:09:41Z"},{"alias_kind":"pith_short_12","alias_value":"LTXEND7SHZA7","created_at":"2026-07-05T07:09:41Z"},{"alias_kind":"pith_short_16","alias_value":"LTXEND7SHZA7L2CV","created_at":"2026-07-05T07:09:41Z"},{"alias_kind":"pith_short_8","alias_value":"LTXEND7S","created_at":"2026-07-05T07:09:41Z"}],"graph_snapshots":[{"event_id":"sha256:a2e979e0541647acdc140b305e6424dcc0a28d97c31b6843dec2952850db3ec8","target":"graph","created_at":"2026-07-05T07:09:41Z","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/2004.14254/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Motivation: Disease diagnosis oriented dialogue system models the interactive consultation procedure as Markov Decision Process and reinforcement learning algorithms are used to solve the problem. Existing approaches usually employ a flat policy structure that treat all symptoms and diseases equally for action making. This strategy works well in the simple scenario when the action space is small, however, its efficiency will be challenged in the real environment. Inspired by the offline consultation process, we propose to integrate a hierarchical policy structure of two levels into the dialogu","authors_text":"Baolin Peng, Cheng Zhong, Jiajie Peng, Kangenbei Liao, Qianlong Liu, Wei Chen, Xuanjing Huang, Zhongyu Wei","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-04-29T15:02:41Z","title":"Hierarchical Reinforcement Learning for Automatic Disease Diagnosis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.14254","kind":"arxiv","version":2},"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":"sha256:7bc5fa0dbed4cbfb0dafb744ae2df2bb1ab8aa8b924b9f70769717bf48a16eb6","target":"record","created_at":"2026-07-05T07:09:41Z","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":"f0a557eacf10878ec70088045e4f27a4341d2e0b10ae324d27238a0c781d1c78","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-04-29T15:02:41Z","title_canon_sha256":"0a11adf5dae90c07f92f9a4b24c52b33858c470667d41cf24585a33a470d546f"},"schema_version":"1.0","source":{"id":"2004.14254","kind":"arxiv","version":2}},"canonical_sha256":"5cee468ff23e41f5e855c9a1655cf08a84ac01ef5107cf8bec424b3dd52a135c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5cee468ff23e41f5e855c9a1655cf08a84ac01ef5107cf8bec424b3dd52a135c","first_computed_at":"2026-07-05T07:09:41.145999Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:09:41.145999Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0H3J1dV7WZSPG+IqmyEguItb3CJjGiS/9NPvkxCtJuR8swzuhEVAj5Yy3N/6sPwdqB+gi4RfBPuDLH12mVnuBg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:09:41.146437Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.14254","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7bc5fa0dbed4cbfb0dafb744ae2df2bb1ab8aa8b924b9f70769717bf48a16eb6","sha256:a2e979e0541647acdc140b305e6424dcc0a28d97c31b6843dec2952850db3ec8"],"state_sha256":"c911f9def4a6291b34c178c9c3aaff10ed72860e8d05f4f7de855758998d3145"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j17KCf4tIicl1n6u6VIKf9bT/1eum+UkRoPS3IFJ7a0QRGZw7c9kJvTOa2Yx1MnhY9EMYsF8WzlIKesyxA9ZDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T12:17:20.583543Z","bundle_sha256":"c5490969d7fb406290b93965c4bec9d6ad0c556151507c9f2a914f630fb8b77a"}}