{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:L6SZKYK2XPXRPT3GBDBMX7NQKJ","short_pith_number":"pith:L6SZKYK2","canonical_record":{"source":{"id":"1606.02560","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2016-06-08T14:03:25Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"83bc6da1451c3bd4620a5de4c016f4b1da9a8bcd249cc2c17e4de1e123e9a3e5","abstract_canon_sha256":"182e63191078388a0e0be70bd0f75b0f6c31d686b3e1b1f2377669f7066c65c8"},"schema_version":"1.0"},"canonical_sha256":"5fa595615abbef17cf6608c2cbfdb052710c3e2b5ab9638fd08f283a10efbb50","source":{"kind":"arxiv","id":"1606.02560","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1606.02560","created_at":"2026-05-18T01:04:32Z"},{"alias_kind":"arxiv_version","alias_value":"1606.02560v2","created_at":"2026-05-18T01:04:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.02560","created_at":"2026-05-18T01:04:32Z"},{"alias_kind":"pith_short_12","alias_value":"L6SZKYK2XPXR","created_at":"2026-05-18T12:30:29Z"},{"alias_kind":"pith_short_16","alias_value":"L6SZKYK2XPXRPT3G","created_at":"2026-05-18T12:30:29Z"},{"alias_kind":"pith_short_8","alias_value":"L6SZKYK2","created_at":"2026-05-18T12:30:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:L6SZKYK2XPXRPT3GBDBMX7NQKJ","target":"record","payload":{"canonical_record":{"source":{"id":"1606.02560","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2016-06-08T14:03:25Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"83bc6da1451c3bd4620a5de4c016f4b1da9a8bcd249cc2c17e4de1e123e9a3e5","abstract_canon_sha256":"182e63191078388a0e0be70bd0f75b0f6c31d686b3e1b1f2377669f7066c65c8"},"schema_version":"1.0"},"canonical_sha256":"5fa595615abbef17cf6608c2cbfdb052710c3e2b5ab9638fd08f283a10efbb50","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:04:32.663908Z","signature_b64":"Xbi+NU0Fgp77DayIUtM9xg2SUUVujwzqUokGzkbcJ1x/WaHGR0WgrdmdDuo/Yyg3NFCYVo4QAGy78hyx76M0Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5fa595615abbef17cf6608c2cbfdb052710c3e2b5ab9638fd08f283a10efbb50","last_reissued_at":"2026-05-18T01:04:32.663194Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:04:32.663194Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1606.02560","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":"2026-05-18T01:04:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vc5KwmBUHQ2n1bCq8sEBLH0exNlTWIpEpmkB432I6+2PZujJGToB2mPIHFGJ3lxvFB/QUttQ0DvFZmiCfONPDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T15:08:10.979996Z"},"content_sha256":"7a203052c6020c43922075eb333fafe9b8413c4b857ab5fcfc355e734402ef4b","schema_version":"1.0","event_id":"sha256:7a203052c6020c43922075eb333fafe9b8413c4b857ab5fcfc355e734402ef4b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:L6SZKYK2XPXRPT3GBDBMX7NQKJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards End-to-End Learning for Dialog State Tracking and Management using Deep Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Maxine Eskenazi, Tiancheng Zhao","submitted_at":"2016-06-08T14:03:25Z","abstract_excerpt":"This paper presents an end-to-end framework for task-oriented dialog systems using a variant of Deep Recurrent Q-Networks (DRQN). The model is able to interface with a relational database and jointly learn policies for both language understanding and dialog strategy. Moreover, we propose a hybrid algorithm that combines the strength of reinforcement learning and supervised learning to achieve faster learning speed. We evaluated the proposed model on a 20 Question Game conversational game simulator. Results show that the proposed method outperforms the modular-based baseline and learns a distri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.02560","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":""},"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":"2026-05-18T01:04:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/g2AcBy+SXdrZ6YT9xuPy8pUhtxRcf6szg4EJ2XTDKzTYPtRi3WOhtluHMrkRiesRBs6/pvd5lnoItXm3lVxCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T15:08:10.980375Z"},"content_sha256":"fc563493eb181b5ca00865862ffa573a68ea7713fe5864045300e95113467a9e","schema_version":"1.0","event_id":"sha256:fc563493eb181b5ca00865862ffa573a68ea7713fe5864045300e95113467a9e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/L6SZKYK2XPXRPT3GBDBMX7NQKJ/bundle.json","state_url":"https://pith.science/pith/L6SZKYK2XPXRPT3GBDBMX7NQKJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/L6SZKYK2XPXRPT3GBDBMX7NQKJ/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":"2026-06-05T15:08:10Z","links":{"resolver":"https://pith.science/pith/L6SZKYK2XPXRPT3GBDBMX7NQKJ","bundle":"https://pith.science/pith/L6SZKYK2XPXRPT3GBDBMX7NQKJ/bundle.json","state":"https://pith.science/pith/L6SZKYK2XPXRPT3GBDBMX7NQKJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/L6SZKYK2XPXRPT3GBDBMX7NQKJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:L6SZKYK2XPXRPT3GBDBMX7NQKJ","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":"182e63191078388a0e0be70bd0f75b0f6c31d686b3e1b1f2377669f7066c65c8","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2016-06-08T14:03:25Z","title_canon_sha256":"83bc6da1451c3bd4620a5de4c016f4b1da9a8bcd249cc2c17e4de1e123e9a3e5"},"schema_version":"1.0","source":{"id":"1606.02560","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1606.02560","created_at":"2026-05-18T01:04:32Z"},{"alias_kind":"arxiv_version","alias_value":"1606.02560v2","created_at":"2026-05-18T01:04:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.02560","created_at":"2026-05-18T01:04:32Z"},{"alias_kind":"pith_short_12","alias_value":"L6SZKYK2XPXR","created_at":"2026-05-18T12:30:29Z"},{"alias_kind":"pith_short_16","alias_value":"L6SZKYK2XPXRPT3G","created_at":"2026-05-18T12:30:29Z"},{"alias_kind":"pith_short_8","alias_value":"L6SZKYK2","created_at":"2026-05-18T12:30:29Z"}],"graph_snapshots":[{"event_id":"sha256:fc563493eb181b5ca00865862ffa573a68ea7713fe5864045300e95113467a9e","target":"graph","created_at":"2026-05-18T01:04:32Z","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":"This paper presents an end-to-end framework for task-oriented dialog systems using a variant of Deep Recurrent Q-Networks (DRQN). The model is able to interface with a relational database and jointly learn policies for both language understanding and dialog strategy. Moreover, we propose a hybrid algorithm that combines the strength of reinforcement learning and supervised learning to achieve faster learning speed. We evaluated the proposed model on a 20 Question Game conversational game simulator. Results show that the proposed method outperforms the modular-based baseline and learns a distri","authors_text":"Maxine Eskenazi, Tiancheng Zhao","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2016-06-08T14:03:25Z","title":"Towards End-to-End Learning for Dialog State Tracking and Management using Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.02560","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":"sha256:7a203052c6020c43922075eb333fafe9b8413c4b857ab5fcfc355e734402ef4b","target":"record","created_at":"2026-05-18T01:04:32Z","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":"182e63191078388a0e0be70bd0f75b0f6c31d686b3e1b1f2377669f7066c65c8","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2016-06-08T14:03:25Z","title_canon_sha256":"83bc6da1451c3bd4620a5de4c016f4b1da9a8bcd249cc2c17e4de1e123e9a3e5"},"schema_version":"1.0","source":{"id":"1606.02560","kind":"arxiv","version":2}},"canonical_sha256":"5fa595615abbef17cf6608c2cbfdb052710c3e2b5ab9638fd08f283a10efbb50","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5fa595615abbef17cf6608c2cbfdb052710c3e2b5ab9638fd08f283a10efbb50","first_computed_at":"2026-05-18T01:04:32.663194Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:04:32.663194Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Xbi+NU0Fgp77DayIUtM9xg2SUUVujwzqUokGzkbcJ1x/WaHGR0WgrdmdDuo/Yyg3NFCYVo4QAGy78hyx76M0Dw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:04:32.663908Z","signed_message":"canonical_sha256_bytes"},"source_id":"1606.02560","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7a203052c6020c43922075eb333fafe9b8413c4b857ab5fcfc355e734402ef4b","sha256:fc563493eb181b5ca00865862ffa573a68ea7713fe5864045300e95113467a9e"],"state_sha256":"9e286cc54f74e0995c81e12a65a1e4a685d7516355347a1da247a0e7994fac82"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EMkllRosjTuS+kQv6QxG5vEkPdnrgnCrWj0TE3Lkp/n65n3r38Cbny9zuRjE/G+g1lt4tZD2Xr8+1C9eSt/fAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T15:08:10.982329Z","bundle_sha256":"030329207910d737b13e93cf2de486f30ad50ef489d9f3f113965eb2adce88a1"}}