{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:Y5EU567QN4IHL5GG2KXKHDAX7X","short_pith_number":"pith:Y5EU567Q","canonical_record":{"source":{"id":"1707.06299","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-19T21:21:03Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"39d6dcdb5836817c160f61566e19285af9f455f85124a6bdb3db88bd02808c89","abstract_canon_sha256":"ecc52da10f29a777c756723e701f95d6f3f07e3d0474a17b846a7ccbbd02ca51"},"schema_version":"1.0"},"canonical_sha256":"c7494efbf06f1075f4c6d2aea38c17fdf5008e9617c62ebcd9d51c445c601004","source":{"kind":"arxiv","id":"1707.06299","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.06299","created_at":"2026-05-18T00:39:54Z"},{"alias_kind":"arxiv_version","alias_value":"1707.06299v1","created_at":"2026-05-18T00:39:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.06299","created_at":"2026-05-18T00:39:54Z"},{"alias_kind":"pith_short_12","alias_value":"Y5EU567QN4IH","created_at":"2026-05-18T12:31:56Z"},{"alias_kind":"pith_short_16","alias_value":"Y5EU567QN4IHL5GG","created_at":"2026-05-18T12:31:56Z"},{"alias_kind":"pith_short_8","alias_value":"Y5EU567Q","created_at":"2026-05-18T12:31:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:Y5EU567QN4IHL5GG2KXKHDAX7X","target":"record","payload":{"canonical_record":{"source":{"id":"1707.06299","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-19T21:21:03Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"39d6dcdb5836817c160f61566e19285af9f455f85124a6bdb3db88bd02808c89","abstract_canon_sha256":"ecc52da10f29a777c756723e701f95d6f3f07e3d0474a17b846a7ccbbd02ca51"},"schema_version":"1.0"},"canonical_sha256":"c7494efbf06f1075f4c6d2aea38c17fdf5008e9617c62ebcd9d51c445c601004","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:39:54.217493Z","signature_b64":"sOzWj1Gi6P+6vfyh6vXMl5bNEX4elZi55mgNrpxvvgTVX6f56/1PYSHVrARyCWvVgX0SGlHHHl7NSyrl04qYCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7494efbf06f1075f4c6d2aea38c17fdf5008e9617c62ebcd9d51c445c601004","last_reissued_at":"2026-05-18T00:39:54.216807Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:39:54.216807Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1707.06299","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":"2026-05-18T00:39:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Vub3V+Wk+LYB3TJyGVbQnYAvW4ztjizsURQfPmNaDnU3407sSV/jEIz6UUkab9pvrzqMcNsPBmrA87fpJQwiCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T19:23:38.051988Z"},"content_sha256":"c201baf23905ecab8b37209e83d93e61b9926214c634d6b3650103fcaa038040","schema_version":"1.0","event_id":"sha256:c201baf23905ecab8b37209e83d93e61b9926214c634d6b3650103fcaa038040"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:Y5EU567QN4IHL5GG2KXKHDAX7X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reward-Balancing for Statistical Spoken Dialogue Systems using Multi-objective Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.CL","authors_text":"I\\~nigo Casanueva, Lina Rojas-Barahona, Milica Ga\\v{s}i\\'c, Nikola Mrk\\v{s}i\\'c, Pawe{\\l} Budzianowski, Pei-Hao Su, Stefan Ultes, Steve Young, Tsung-Hsien Wen","submitted_at":"2017-07-19T21:21:03Z","abstract_excerpt":"Reinforcement learning is widely used for dialogue policy optimization where the reward function often consists of more than one component, e.g., the dialogue success and the dialogue length. In this work, we propose a structured method for finding a good balance between these components by searching for the optimal reward component weighting. To render this search feasible, we use multi-objective reinforcement learning to significantly reduce the number of training dialogues required. We apply our proposed method to find optimized component weights for six domains and compare them to a defaul"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.06299","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":""},"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":"2026-05-18T00:39:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VXQye8oV0sfsZETs4yIsu63uguZgGlDv0sVdSAoBk/otxNHfeSIUQ70998OtiPJhH8KjDxTILTD/9Egh4NzSDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T19:23:38.052706Z"},"content_sha256":"c5baf4bd4c46c8f1888578bdf0207b508a6f4d55098800971da7c87ab712dbfd","schema_version":"1.0","event_id":"sha256:c5baf4bd4c46c8f1888578bdf0207b508a6f4d55098800971da7c87ab712dbfd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y5EU567QN4IHL5GG2KXKHDAX7X/bundle.json","state_url":"https://pith.science/pith/Y5EU567QN4IHL5GG2KXKHDAX7X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y5EU567QN4IHL5GG2KXKHDAX7X/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":"2026-05-29T19:23:38Z","links":{"resolver":"https://pith.science/pith/Y5EU567QN4IHL5GG2KXKHDAX7X","bundle":"https://pith.science/pith/Y5EU567QN4IHL5GG2KXKHDAX7X/bundle.json","state":"https://pith.science/pith/Y5EU567QN4IHL5GG2KXKHDAX7X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y5EU567QN4IHL5GG2KXKHDAX7X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:Y5EU567QN4IHL5GG2KXKHDAX7X","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":"ecc52da10f29a777c756723e701f95d6f3f07e3d0474a17b846a7ccbbd02ca51","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-19T21:21:03Z","title_canon_sha256":"39d6dcdb5836817c160f61566e19285af9f455f85124a6bdb3db88bd02808c89"},"schema_version":"1.0","source":{"id":"1707.06299","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.06299","created_at":"2026-05-18T00:39:54Z"},{"alias_kind":"arxiv_version","alias_value":"1707.06299v1","created_at":"2026-05-18T00:39:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.06299","created_at":"2026-05-18T00:39:54Z"},{"alias_kind":"pith_short_12","alias_value":"Y5EU567QN4IH","created_at":"2026-05-18T12:31:56Z"},{"alias_kind":"pith_short_16","alias_value":"Y5EU567QN4IHL5GG","created_at":"2026-05-18T12:31:56Z"},{"alias_kind":"pith_short_8","alias_value":"Y5EU567Q","created_at":"2026-05-18T12:31:56Z"}],"graph_snapshots":[{"event_id":"sha256:c5baf4bd4c46c8f1888578bdf0207b508a6f4d55098800971da7c87ab712dbfd","target":"graph","created_at":"2026-05-18T00:39:54Z","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":"Reinforcement learning is widely used for dialogue policy optimization where the reward function often consists of more than one component, e.g., the dialogue success and the dialogue length. In this work, we propose a structured method for finding a good balance between these components by searching for the optimal reward component weighting. To render this search feasible, we use multi-objective reinforcement learning to significantly reduce the number of training dialogues required. We apply our proposed method to find optimized component weights for six domains and compare them to a defaul","authors_text":"I\\~nigo Casanueva, Lina Rojas-Barahona, Milica Ga\\v{s}i\\'c, Nikola Mrk\\v{s}i\\'c, Pawe{\\l} Budzianowski, Pei-Hao Su, Stefan Ultes, Steve Young, Tsung-Hsien Wen","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-19T21:21:03Z","title":"Reward-Balancing for Statistical Spoken Dialogue Systems using Multi-objective Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.06299","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:c201baf23905ecab8b37209e83d93e61b9926214c634d6b3650103fcaa038040","target":"record","created_at":"2026-05-18T00:39:54Z","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":"ecc52da10f29a777c756723e701f95d6f3f07e3d0474a17b846a7ccbbd02ca51","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-19T21:21:03Z","title_canon_sha256":"39d6dcdb5836817c160f61566e19285af9f455f85124a6bdb3db88bd02808c89"},"schema_version":"1.0","source":{"id":"1707.06299","kind":"arxiv","version":1}},"canonical_sha256":"c7494efbf06f1075f4c6d2aea38c17fdf5008e9617c62ebcd9d51c445c601004","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c7494efbf06f1075f4c6d2aea38c17fdf5008e9617c62ebcd9d51c445c601004","first_computed_at":"2026-05-18T00:39:54.216807Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:39:54.216807Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sOzWj1Gi6P+6vfyh6vXMl5bNEX4elZi55mgNrpxvvgTVX6f56/1PYSHVrARyCWvVgX0SGlHHHl7NSyrl04qYCA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:39:54.217493Z","signed_message":"canonical_sha256_bytes"},"source_id":"1707.06299","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c201baf23905ecab8b37209e83d93e61b9926214c634d6b3650103fcaa038040","sha256:c5baf4bd4c46c8f1888578bdf0207b508a6f4d55098800971da7c87ab712dbfd"],"state_sha256":"939664548e41b035971824de8e560a927c8977ce325bede2914fcf0f0dbb0479"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QDCssFYFoO6a7032qb5VjJz6mq0iKE3Q0/0mQFGLy58PlBBqxsaqTTNvBFaBzu+f8pZ0ydBhmT8HrvAu2SFKBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-29T19:23:38.058667Z","bundle_sha256":"30f7ced941227bf190e0f1d9b6677de09a2e93fb44178023b0faf0ccfb9dd8c9"}}