{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:HTYYCEYT5LB5KYJHW3HWGOV4GH","short_pith_number":"pith:HTYYCEYT","canonical_record":{"source":{"id":"1606.03152","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-06-10T01:02:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"57fdf8164a75e97e61f00082d240095d08a146d13754846ac7bbc54a98af9721","abstract_canon_sha256":"acc7fdc033e2deb323baf91e5c770a7dc6bfea2bc9398d6d3aec297e97cf7531"},"schema_version":"1.0"},"canonical_sha256":"3cf1811313eac3d56127b6cf633abc31c9c9498d1669e84286499c6234992a75","source":{"kind":"arxiv","id":"1606.03152","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1606.03152","created_at":"2026-05-18T01:04:49Z"},{"alias_kind":"arxiv_version","alias_value":"1606.03152v4","created_at":"2026-05-18T01:04:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.03152","created_at":"2026-05-18T01:04:49Z"},{"alias_kind":"pith_short_12","alias_value":"HTYYCEYT5LB5","created_at":"2026-05-18T12:30:22Z"},{"alias_kind":"pith_short_16","alias_value":"HTYYCEYT5LB5KYJH","created_at":"2026-05-18T12:30:22Z"},{"alias_kind":"pith_short_8","alias_value":"HTYYCEYT","created_at":"2026-05-18T12:30:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:HTYYCEYT5LB5KYJHW3HWGOV4GH","target":"record","payload":{"canonical_record":{"source":{"id":"1606.03152","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-06-10T01:02:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"57fdf8164a75e97e61f00082d240095d08a146d13754846ac7bbc54a98af9721","abstract_canon_sha256":"acc7fdc033e2deb323baf91e5c770a7dc6bfea2bc9398d6d3aec297e97cf7531"},"schema_version":"1.0"},"canonical_sha256":"3cf1811313eac3d56127b6cf633abc31c9c9498d1669e84286499c6234992a75","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:04:49.695470Z","signature_b64":"1GmifWcLPOMI+YTSaHpd0D0eVKjNiRa5bs7c05fUfLpLMZVEXFm/1lcqScfReqvSlP841mxR1U/zWo9SEWuKDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3cf1811313eac3d56127b6cf633abc31c9c9498d1669e84286499c6234992a75","last_reissued_at":"2026-05-18T01:04:49.694961Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:04:49.694961Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1606.03152","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:04:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TErpSaZX2hpfQZG+Ji7dpvm6g9rcq5wvqtCLbUyOmMseFKVSWJBIuWyjw/bO/HofWGvZvYJj9aUvrmcQd0rXCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T04:02:38.252974Z"},"content_sha256":"0127413c8cc5ab0883de16bb6fba8771b7c3305d4e47fa30580aa516261a7910","schema_version":"1.0","event_id":"sha256:0127413c8cc5ab0883de16bb6fba8771b7c3305d4e47fa30580aa516261a7910"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:HTYYCEYT5LB5KYJHW3HWGOV4GH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Policy Networks with Two-Stage Training for Dialogue Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hannes Schulz, Jing He, Kaheer Suleman, Layla El Asri, Mehdi Fatemi","submitted_at":"2016-06-10T01:02:19Z","abstract_excerpt":"In this paper, we propose to use deep policy networks which are trained with an advantage actor-critic method for statistically optimised dialogue systems. First, we show that, on summary state and action spaces, deep Reinforcement Learning (RL) outperforms Gaussian Processes methods. Summary state and action spaces lead to good performance but require pre-engineering effort, RL knowledge, and domain expertise. In order to remove the need to define such summary spaces, we show that deep RL can also be trained efficiently on the original state and action spaces. Dialogue systems based on partia"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.03152","kind":"arxiv","version":4},"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":"2026-05-18T01:04:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FAqmzLBmXsAZGof37pFuco3sl/fpegcAxeMIeXJ3KNNEeRKgUZDUB3OtE4tuekn57AXkXk1xdMm0MqfEd4A1DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T04:02:38.253340Z"},"content_sha256":"2676013d10b1aba3223535f233ee43b47208a1e013d2690cac59af4cf9c78766","schema_version":"1.0","event_id":"sha256:2676013d10b1aba3223535f233ee43b47208a1e013d2690cac59af4cf9c78766"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HTYYCEYT5LB5KYJHW3HWGOV4GH/bundle.json","state_url":"https://pith.science/pith/HTYYCEYT5LB5KYJHW3HWGOV4GH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HTYYCEYT5LB5KYJHW3HWGOV4GH/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":"2026-05-28T04:02:38Z","links":{"resolver":"https://pith.science/pith/HTYYCEYT5LB5KYJHW3HWGOV4GH","bundle":"https://pith.science/pith/HTYYCEYT5LB5KYJHW3HWGOV4GH/bundle.json","state":"https://pith.science/pith/HTYYCEYT5LB5KYJHW3HWGOV4GH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HTYYCEYT5LB5KYJHW3HWGOV4GH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:HTYYCEYT5LB5KYJHW3HWGOV4GH","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":"acc7fdc033e2deb323baf91e5c770a7dc6bfea2bc9398d6d3aec297e97cf7531","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-06-10T01:02:19Z","title_canon_sha256":"57fdf8164a75e97e61f00082d240095d08a146d13754846ac7bbc54a98af9721"},"schema_version":"1.0","source":{"id":"1606.03152","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1606.03152","created_at":"2026-05-18T01:04:49Z"},{"alias_kind":"arxiv_version","alias_value":"1606.03152v4","created_at":"2026-05-18T01:04:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.03152","created_at":"2026-05-18T01:04:49Z"},{"alias_kind":"pith_short_12","alias_value":"HTYYCEYT5LB5","created_at":"2026-05-18T12:30:22Z"},{"alias_kind":"pith_short_16","alias_value":"HTYYCEYT5LB5KYJH","created_at":"2026-05-18T12:30:22Z"},{"alias_kind":"pith_short_8","alias_value":"HTYYCEYT","created_at":"2026-05-18T12:30:22Z"}],"graph_snapshots":[{"event_id":"sha256:2676013d10b1aba3223535f233ee43b47208a1e013d2690cac59af4cf9c78766","target":"graph","created_at":"2026-05-18T01:04:49Z","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":"In this paper, we propose to use deep policy networks which are trained with an advantage actor-critic method for statistically optimised dialogue systems. First, we show that, on summary state and action spaces, deep Reinforcement Learning (RL) outperforms Gaussian Processes methods. Summary state and action spaces lead to good performance but require pre-engineering effort, RL knowledge, and domain expertise. In order to remove the need to define such summary spaces, we show that deep RL can also be trained efficiently on the original state and action spaces. Dialogue systems based on partia","authors_text":"Hannes Schulz, Jing He, Kaheer Suleman, Layla El Asri, Mehdi Fatemi","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-06-10T01:02:19Z","title":"Policy Networks with Two-Stage Training for Dialogue Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.03152","kind":"arxiv","version":4},"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":"sha256:0127413c8cc5ab0883de16bb6fba8771b7c3305d4e47fa30580aa516261a7910","target":"record","created_at":"2026-05-18T01:04:49Z","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":"acc7fdc033e2deb323baf91e5c770a7dc6bfea2bc9398d6d3aec297e97cf7531","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-06-10T01:02:19Z","title_canon_sha256":"57fdf8164a75e97e61f00082d240095d08a146d13754846ac7bbc54a98af9721"},"schema_version":"1.0","source":{"id":"1606.03152","kind":"arxiv","version":4}},"canonical_sha256":"3cf1811313eac3d56127b6cf633abc31c9c9498d1669e84286499c6234992a75","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3cf1811313eac3d56127b6cf633abc31c9c9498d1669e84286499c6234992a75","first_computed_at":"2026-05-18T01:04:49.694961Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:04:49.694961Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1GmifWcLPOMI+YTSaHpd0D0eVKjNiRa5bs7c05fUfLpLMZVEXFm/1lcqScfReqvSlP841mxR1U/zWo9SEWuKDg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:04:49.695470Z","signed_message":"canonical_sha256_bytes"},"source_id":"1606.03152","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0127413c8cc5ab0883de16bb6fba8771b7c3305d4e47fa30580aa516261a7910","sha256:2676013d10b1aba3223535f233ee43b47208a1e013d2690cac59af4cf9c78766"],"state_sha256":"c8bead48ffcbddd98bcdd3d83a380ebae3b1f7674f3c81adeb02b896f2959268"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aVJe9N898JG6v8vlf7mSZHHxTmxv8C0CSbdgRkcnQtRq6Avx/tpI+O1oizXIZ7JrFgRVT5TPfjdAHvpn0yotDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T04:02:38.255403Z","bundle_sha256":"848aba50a4b0574a21f8d2a43a75b5b18243f46d689dbdcfa37f8e90b586c77b"}}