{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:GTYJS5JDRBSJE3OQMYODS7DFWR","short_pith_number":"pith:GTYJS5JD","canonical_record":{"source":{"id":"1711.08493","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-11-22T20:15:01Z","cross_cats_sorted":[],"title_canon_sha256":"e55bc0944f8857a65452026bc83b405fce2e82adeb1029596b0fd85dd4971179","abstract_canon_sha256":"addc901f7cffb6ff43f70b116113ee1d04636c24a6147e915037b20041240b79"},"schema_version":"1.0"},"canonical_sha256":"34f09975238864926dd0661c397c65b46c2e47bb5a61940b163019b4c80a103a","source":{"kind":"arxiv","id":"1711.08493","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.08493","created_at":"2026-05-18T00:29:44Z"},{"alias_kind":"arxiv_version","alias_value":"1711.08493v1","created_at":"2026-05-18T00:29:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.08493","created_at":"2026-05-18T00:29:44Z"},{"alias_kind":"pith_short_12","alias_value":"GTYJS5JDRBSJ","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_16","alias_value":"GTYJS5JDRBSJE3OQ","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_8","alias_value":"GTYJS5JD","created_at":"2026-05-18T12:31:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:GTYJS5JDRBSJE3OQMYODS7DFWR","target":"record","payload":{"canonical_record":{"source":{"id":"1711.08493","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-11-22T20:15:01Z","cross_cats_sorted":[],"title_canon_sha256":"e55bc0944f8857a65452026bc83b405fce2e82adeb1029596b0fd85dd4971179","abstract_canon_sha256":"addc901f7cffb6ff43f70b116113ee1d04636c24a6147e915037b20041240b79"},"schema_version":"1.0"},"canonical_sha256":"34f09975238864926dd0661c397c65b46c2e47bb5a61940b163019b4c80a103a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:29:44.947369Z","signature_b64":"gTIYSG+Ey+0fx1saRTLU6BmClU6vGIXGh9vlUq6hl6B213mXnG2waPAO2eKrizr0wh+1eHPdwIKZQeHLAlTnDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34f09975238864926dd0661c397c65b46c2e47bb5a61940b163019b4c80a103a","last_reissued_at":"2026-05-18T00:29:44.946721Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:29:44.946721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1711.08493","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":"2026-05-18T00:29:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+zaSE1PzhJiklPvtbenVLtehRhn8mvFFK7Hn3G1JTzZ92hCzOuUnJcTqFAzJgcBCbmqcLNxh/0KQKkoiWUxhBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T10:41:17.998409Z"},"content_sha256":"5daceef0b410f9d50c53f38ad036223e1dc874e25cc0f504e61d4ec04eecaf90","schema_version":"1.0","event_id":"sha256:5daceef0b410f9d50c53f38ad036223e1dc874e25cc0f504e61d4ec04eecaf90"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:GTYJS5JDRBSJE3OQMYODS7DFWR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Customized Nonlinear Bandits for Online Response Selection in Neural Conversation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bing Liu, Ian Lane, Ole J. Mengshoel, Tong Yu","submitted_at":"2017-11-22T20:15:01Z","abstract_excerpt":"Dialog response selection is an important step towards natural response generation in conversational agents. Existing work on neural conversational models mainly focuses on offline supervised learning using a large set of context-response pairs. In this paper, we focus on online learning of response selection in retrieval-based dialog systems. We propose a contextual multi-armed bandit model with a nonlinear reward function that uses distributed representation of text for online response selection. A bidirectional LSTM is used to produce the distributed representations of dialog context and re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.08493","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":"2026-05-18T00:29:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1vvY0FB2VDN9RrxbJw+ecQF2IMFbEvpOWh+7rM5Ner6Dm6jyIsNsNZ80CorDLvSSi4DLikO2BkyBSmua5+mMDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T10:41:17.998754Z"},"content_sha256":"8b202cc7a4fc06661808183cd98984493f8e57545e68694ef229b20519ce2bec","schema_version":"1.0","event_id":"sha256:8b202cc7a4fc06661808183cd98984493f8e57545e68694ef229b20519ce2bec"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GTYJS5JDRBSJE3OQMYODS7DFWR/bundle.json","state_url":"https://pith.science/pith/GTYJS5JDRBSJE3OQMYODS7DFWR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GTYJS5JDRBSJE3OQMYODS7DFWR/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":"2026-06-12T10:41:18Z","links":{"resolver":"https://pith.science/pith/GTYJS5JDRBSJE3OQMYODS7DFWR","bundle":"https://pith.science/pith/GTYJS5JDRBSJE3OQMYODS7DFWR/bundle.json","state":"https://pith.science/pith/GTYJS5JDRBSJE3OQMYODS7DFWR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GTYJS5JDRBSJE3OQMYODS7DFWR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:GTYJS5JDRBSJE3OQMYODS7DFWR","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":"addc901f7cffb6ff43f70b116113ee1d04636c24a6147e915037b20041240b79","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-11-22T20:15:01Z","title_canon_sha256":"e55bc0944f8857a65452026bc83b405fce2e82adeb1029596b0fd85dd4971179"},"schema_version":"1.0","source":{"id":"1711.08493","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.08493","created_at":"2026-05-18T00:29:44Z"},{"alias_kind":"arxiv_version","alias_value":"1711.08493v1","created_at":"2026-05-18T00:29:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.08493","created_at":"2026-05-18T00:29:44Z"},{"alias_kind":"pith_short_12","alias_value":"GTYJS5JDRBSJ","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_16","alias_value":"GTYJS5JDRBSJE3OQ","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_8","alias_value":"GTYJS5JD","created_at":"2026-05-18T12:31:18Z"}],"graph_snapshots":[{"event_id":"sha256:8b202cc7a4fc06661808183cd98984493f8e57545e68694ef229b20519ce2bec","target":"graph","created_at":"2026-05-18T00:29:44Z","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":"Dialog response selection is an important step towards natural response generation in conversational agents. Existing work on neural conversational models mainly focuses on offline supervised learning using a large set of context-response pairs. In this paper, we focus on online learning of response selection in retrieval-based dialog systems. We propose a contextual multi-armed bandit model with a nonlinear reward function that uses distributed representation of text for online response selection. A bidirectional LSTM is used to produce the distributed representations of dialog context and re","authors_text":"Bing Liu, Ian Lane, Ole J. Mengshoel, Tong Yu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-11-22T20:15:01Z","title":"Customized Nonlinear Bandits for Online Response Selection in Neural Conversation Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.08493","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":"sha256:5daceef0b410f9d50c53f38ad036223e1dc874e25cc0f504e61d4ec04eecaf90","target":"record","created_at":"2026-05-18T00:29:44Z","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":"addc901f7cffb6ff43f70b116113ee1d04636c24a6147e915037b20041240b79","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-11-22T20:15:01Z","title_canon_sha256":"e55bc0944f8857a65452026bc83b405fce2e82adeb1029596b0fd85dd4971179"},"schema_version":"1.0","source":{"id":"1711.08493","kind":"arxiv","version":1}},"canonical_sha256":"34f09975238864926dd0661c397c65b46c2e47bb5a61940b163019b4c80a103a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"34f09975238864926dd0661c397c65b46c2e47bb5a61940b163019b4c80a103a","first_computed_at":"2026-05-18T00:29:44.946721Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:29:44.946721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gTIYSG+Ey+0fx1saRTLU6BmClU6vGIXGh9vlUq6hl6B213mXnG2waPAO2eKrizr0wh+1eHPdwIKZQeHLAlTnDw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:29:44.947369Z","signed_message":"canonical_sha256_bytes"},"source_id":"1711.08493","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5daceef0b410f9d50c53f38ad036223e1dc874e25cc0f504e61d4ec04eecaf90","sha256:8b202cc7a4fc06661808183cd98984493f8e57545e68694ef229b20519ce2bec"],"state_sha256":"05ba36a90dfb867a81d08c07bc18ee5daa3b515bdafc61b2d8f8abd36dd68f4d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"stYDq59u8Ufmr3JCRgOdGf+oDn+ghcwehs/lVHUb42YaVcHX2jF4UlFj/vH8FXfV1tXZ/PohHI45i4Ql7tXlAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-12T10:41:18.001137Z","bundle_sha256":"16e337de7e34161c99f559dda0ba7c6eae489ef392fa1ec4f828f0c5f50afb42"}}