{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:YDMIXGKD5BG65MAJS5TKPJ3UCU","short_pith_number":"pith:YDMIXGKD","canonical_record":{"source":{"id":"1811.06630","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-15T23:47:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f9965d5fa713b344114207a27c6f31e6f17c58b90f6fccb25072077bdeef5e03","abstract_canon_sha256":"5b48e8ac1aadfd6eced0404e65de70b82319583c66adc98b4ac72c9b23c232e4"},"schema_version":"1.0"},"canonical_sha256":"c0d88b9943e84deeb0099766a7a7741527e9ad29cf46f1a6b805a6425195e7b4","source":{"kind":"arxiv","id":"1811.06630","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.06630","created_at":"2026-05-18T00:00:34Z"},{"alias_kind":"arxiv_version","alias_value":"1811.06630v1","created_at":"2026-05-18T00:00:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.06630","created_at":"2026-05-18T00:00:34Z"},{"alias_kind":"pith_short_12","alias_value":"YDMIXGKD5BG6","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"YDMIXGKD5BG65MAJ","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"YDMIXGKD","created_at":"2026-05-18T12:33:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:YDMIXGKD5BG65MAJS5TKPJ3UCU","target":"record","payload":{"canonical_record":{"source":{"id":"1811.06630","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-15T23:47:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f9965d5fa713b344114207a27c6f31e6f17c58b90f6fccb25072077bdeef5e03","abstract_canon_sha256":"5b48e8ac1aadfd6eced0404e65de70b82319583c66adc98b4ac72c9b23c232e4"},"schema_version":"1.0"},"canonical_sha256":"c0d88b9943e84deeb0099766a7a7741527e9ad29cf46f1a6b805a6425195e7b4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:00:34.308642Z","signature_b64":"4DLYp+WrRDloB3OgbyKubQEzbRUILDDgIWLgXmXIP2vNIFCteikjG4gj2A31CcgXjzGViNz0vbxzjMhb1OHDBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0d88b9943e84deeb0099766a7a7741527e9ad29cf46f1a6b805a6425195e7b4","last_reissued_at":"2026-05-18T00:00:34.307945Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:00:34.307945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.06630","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":"2026-05-18T00:00:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1u3iqqqTCHgsq2Kmf353HHsRnT5ZWW9E9zA4dkYo3wSwyxdrtBTNZUW2CywrE43HovlB5kXrIKHNRcQog1zICQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T21:05:39.327709Z"},"content_sha256":"614fdc3821e40e7ca4c3e9386225000995a5574afcffce621e0b4accc59254ad","schema_version":"1.0","event_id":"sha256:614fdc3821e40e7ca4c3e9386225000995a5574afcffce621e0b4accc59254ad"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:YDMIXGKD5BG65MAJS5TKPJ3UCU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Nudging Neural Conversational Model with Domain Knowledge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Sungjin Lee","submitted_at":"2018-11-15T23:47:39Z","abstract_excerpt":"Neural conversation models are attractive because one can train a model directly on dialog examples with minimal labeling. With a small amount of data, however, they often fail to generalize over test data since they tend to capture spurious features instead of semantically meaningful domain knowledge. To address this issue, we propose a novel approach that allows any human teachers to transfer their domain knowledge to the conversation model in the form of natural language rules. We tested our method with three different dialog datasets. The improved performance across all domains demonstrate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.06630","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":"2026-05-18T00:00:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FJE/exc44b2OytHIa+xmYXxN9i3FBeoir4Tg8P7M9f+wyekS1YrrfggFTmkniu39q2eAWyhVREoy5AB2nmirDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T21:05:39.328445Z"},"content_sha256":"3baf51aec27d05ebf9cd0786d32496b02e82f70fa2211ad295e2c929692f23e5","schema_version":"1.0","event_id":"sha256:3baf51aec27d05ebf9cd0786d32496b02e82f70fa2211ad295e2c929692f23e5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YDMIXGKD5BG65MAJS5TKPJ3UCU/bundle.json","state_url":"https://pith.science/pith/YDMIXGKD5BG65MAJS5TKPJ3UCU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YDMIXGKD5BG65MAJS5TKPJ3UCU/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":"2026-05-25T21:05:39Z","links":{"resolver":"https://pith.science/pith/YDMIXGKD5BG65MAJS5TKPJ3UCU","bundle":"https://pith.science/pith/YDMIXGKD5BG65MAJS5TKPJ3UCU/bundle.json","state":"https://pith.science/pith/YDMIXGKD5BG65MAJS5TKPJ3UCU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YDMIXGKD5BG65MAJS5TKPJ3UCU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:YDMIXGKD5BG65MAJS5TKPJ3UCU","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":"5b48e8ac1aadfd6eced0404e65de70b82319583c66adc98b4ac72c9b23c232e4","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-15T23:47:39Z","title_canon_sha256":"f9965d5fa713b344114207a27c6f31e6f17c58b90f6fccb25072077bdeef5e03"},"schema_version":"1.0","source":{"id":"1811.06630","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.06630","created_at":"2026-05-18T00:00:34Z"},{"alias_kind":"arxiv_version","alias_value":"1811.06630v1","created_at":"2026-05-18T00:00:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.06630","created_at":"2026-05-18T00:00:34Z"},{"alias_kind":"pith_short_12","alias_value":"YDMIXGKD5BG6","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"YDMIXGKD5BG65MAJ","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"YDMIXGKD","created_at":"2026-05-18T12:33:04Z"}],"graph_snapshots":[{"event_id":"sha256:3baf51aec27d05ebf9cd0786d32496b02e82f70fa2211ad295e2c929692f23e5","target":"graph","created_at":"2026-05-18T00:00:34Z","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":"Neural conversation models are attractive because one can train a model directly on dialog examples with minimal labeling. With a small amount of data, however, they often fail to generalize over test data since they tend to capture spurious features instead of semantically meaningful domain knowledge. To address this issue, we propose a novel approach that allows any human teachers to transfer their domain knowledge to the conversation model in the form of natural language rules. We tested our method with three different dialog datasets. The improved performance across all domains demonstrate","authors_text":"Sungjin Lee","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-15T23:47:39Z","title":"Nudging Neural Conversational Model with Domain Knowledge"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.06630","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":"sha256:614fdc3821e40e7ca4c3e9386225000995a5574afcffce621e0b4accc59254ad","target":"record","created_at":"2026-05-18T00:00:34Z","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":"5b48e8ac1aadfd6eced0404e65de70b82319583c66adc98b4ac72c9b23c232e4","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-15T23:47:39Z","title_canon_sha256":"f9965d5fa713b344114207a27c6f31e6f17c58b90f6fccb25072077bdeef5e03"},"schema_version":"1.0","source":{"id":"1811.06630","kind":"arxiv","version":1}},"canonical_sha256":"c0d88b9943e84deeb0099766a7a7741527e9ad29cf46f1a6b805a6425195e7b4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c0d88b9943e84deeb0099766a7a7741527e9ad29cf46f1a6b805a6425195e7b4","first_computed_at":"2026-05-18T00:00:34.307945Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:00:34.307945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4DLYp+WrRDloB3OgbyKubQEzbRUILDDgIWLgXmXIP2vNIFCteikjG4gj2A31CcgXjzGViNz0vbxzjMhb1OHDBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:00:34.308642Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.06630","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:614fdc3821e40e7ca4c3e9386225000995a5574afcffce621e0b4accc59254ad","sha256:3baf51aec27d05ebf9cd0786d32496b02e82f70fa2211ad295e2c929692f23e5"],"state_sha256":"e968c91f02860ecccf8baa7188d657003c97664f732d588c9c35ffcfb161736c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wram2jFvbtTonGmeA70zzJWNe14w25pUOIcODATqEgoZCWgVH7dBSrN4ZhBgBYV5HS5H6uoDpa8uracparmhCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T21:05:39.332085Z","bundle_sha256":"da9aad1ce205cdd50dca9ab792671695e746570b89c31bcd4955c7df8a48be51"}}