{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:4K5NDT25RUOORLKIBU5RZJGULU","short_pith_number":"pith:4K5NDT25","canonical_record":{"source":{"id":"1905.05644","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-14T14:35:06Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"164684f8c2886d74b5630bfdb9021d93b6d6e0f7ebb5cddba15de65f377c5928","abstract_canon_sha256":"76989179b207053824b9a7dbb1fefc1418468358fcb5075ac1d6f89d326f1f1c"},"schema_version":"1.0"},"canonical_sha256":"e2bad1cf5d8d1ce8ad480d3b1ca4d45d156f9857324cf0e204950e09e2ceefb2","source":{"kind":"arxiv","id":"1905.05644","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.05644","created_at":"2026-05-17T23:46:13Z"},{"alias_kind":"arxiv_version","alias_value":"1905.05644v1","created_at":"2026-05-17T23:46:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.05644","created_at":"2026-05-17T23:46:13Z"},{"alias_kind":"pith_short_12","alias_value":"4K5NDT25RUOO","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"4K5NDT25RUOORLKI","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"4K5NDT25","created_at":"2026-05-18T12:33:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:4K5NDT25RUOORLKIBU5RZJGULU","target":"record","payload":{"canonical_record":{"source":{"id":"1905.05644","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-14T14:35:06Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"164684f8c2886d74b5630bfdb9021d93b6d6e0f7ebb5cddba15de65f377c5928","abstract_canon_sha256":"76989179b207053824b9a7dbb1fefc1418468358fcb5075ac1d6f89d326f1f1c"},"schema_version":"1.0"},"canonical_sha256":"e2bad1cf5d8d1ce8ad480d3b1ca4d45d156f9857324cf0e204950e09e2ceefb2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:13.948479Z","signature_b64":"w4cWlqT0byad93BZKbX5gk4OUHbTTucb69t3xTAmgJtn+WoyF5gojZBGTo2c7SxbCZrCl9v0KDRJIt5kGttzDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e2bad1cf5d8d1ce8ad480d3b1ca4d45d156f9857324cf0e204950e09e2ceefb2","last_reissued_at":"2026-05-17T23:46:13.947814Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:13.947814Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.05644","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":"2026-05-17T23:46:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JIJ32JYodWPqpyUWccNtp3jxaC/uhTA394Zr013ym18VNU2GZiRuLtreJ2ImbzdYPr2c81LbQi8TFHSh+k+IBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T12:55:55.298537Z"},"content_sha256":"4f0a77c57fc8b237b3f3f791a9ad1293d501e09b5c893eda786e8fc53f18868d","schema_version":"1.0","event_id":"sha256:4f0a77c57fc8b237b3f3f791a9ad1293d501e09b5c893eda786e8fc53f18868d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:4K5NDT25RUOORLKIBU5RZJGULU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Meta-Learning for Low-resource Natural Language Generation in Task-oriented Dialogue Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Boi Faltings, Fei Mi, Jiyong Zhang, Minlie Huang","submitted_at":"2019-05-14T14:35:06Z","abstract_excerpt":"Natural language generation (NLG) is an essential component of task-oriented dialogue systems. Despite the recent success of neural approaches for NLG, they are typically developed for particular domains with rich annotated training examples. In this paper, we study NLG in a low-resource setting to generate sentences in new scenarios with handful training examples. We formulate the problem from a meta-learning perspective, and propose a generalized optimization-based approach (Meta-NLG) based on the well-recognized model-agnostic meta-learning (MAML) algorithm. Meta-NLG defines a set of meta t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.05644","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":"2026-05-17T23:46:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xY6uGgvNb+ugrkvNhGrECEIT34UYN7mBpHWDOa505iCYdQNDh95DGVtk7f2oO01sK7nQboQWR4CefD2Kif2dCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T12:55:55.298879Z"},"content_sha256":"00c2b892b0ff9d95639ae4bcc6baba9d10cb055039bb351a46a7bc512e2d9be9","schema_version":"1.0","event_id":"sha256:00c2b892b0ff9d95639ae4bcc6baba9d10cb055039bb351a46a7bc512e2d9be9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4K5NDT25RUOORLKIBU5RZJGULU/bundle.json","state_url":"https://pith.science/pith/4K5NDT25RUOORLKIBU5RZJGULU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4K5NDT25RUOORLKIBU5RZJGULU/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":"2026-05-28T12:55:55Z","links":{"resolver":"https://pith.science/pith/4K5NDT25RUOORLKIBU5RZJGULU","bundle":"https://pith.science/pith/4K5NDT25RUOORLKIBU5RZJGULU/bundle.json","state":"https://pith.science/pith/4K5NDT25RUOORLKIBU5RZJGULU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4K5NDT25RUOORLKIBU5RZJGULU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:4K5NDT25RUOORLKIBU5RZJGULU","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":"76989179b207053824b9a7dbb1fefc1418468358fcb5075ac1d6f89d326f1f1c","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-14T14:35:06Z","title_canon_sha256":"164684f8c2886d74b5630bfdb9021d93b6d6e0f7ebb5cddba15de65f377c5928"},"schema_version":"1.0","source":{"id":"1905.05644","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.05644","created_at":"2026-05-17T23:46:13Z"},{"alias_kind":"arxiv_version","alias_value":"1905.05644v1","created_at":"2026-05-17T23:46:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.05644","created_at":"2026-05-17T23:46:13Z"},{"alias_kind":"pith_short_12","alias_value":"4K5NDT25RUOO","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"4K5NDT25RUOORLKI","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"4K5NDT25","created_at":"2026-05-18T12:33:10Z"}],"graph_snapshots":[{"event_id":"sha256:00c2b892b0ff9d95639ae4bcc6baba9d10cb055039bb351a46a7bc512e2d9be9","target":"graph","created_at":"2026-05-17T23:46:13Z","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":"Natural language generation (NLG) is an essential component of task-oriented dialogue systems. Despite the recent success of neural approaches for NLG, they are typically developed for particular domains with rich annotated training examples. In this paper, we study NLG in a low-resource setting to generate sentences in new scenarios with handful training examples. We formulate the problem from a meta-learning perspective, and propose a generalized optimization-based approach (Meta-NLG) based on the well-recognized model-agnostic meta-learning (MAML) algorithm. Meta-NLG defines a set of meta t","authors_text":"Boi Faltings, Fei Mi, Jiyong Zhang, Minlie Huang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-14T14:35:06Z","title":"Meta-Learning for Low-resource Natural Language Generation in Task-oriented Dialogue Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.05644","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":"sha256:4f0a77c57fc8b237b3f3f791a9ad1293d501e09b5c893eda786e8fc53f18868d","target":"record","created_at":"2026-05-17T23:46:13Z","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":"76989179b207053824b9a7dbb1fefc1418468358fcb5075ac1d6f89d326f1f1c","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-14T14:35:06Z","title_canon_sha256":"164684f8c2886d74b5630bfdb9021d93b6d6e0f7ebb5cddba15de65f377c5928"},"schema_version":"1.0","source":{"id":"1905.05644","kind":"arxiv","version":1}},"canonical_sha256":"e2bad1cf5d8d1ce8ad480d3b1ca4d45d156f9857324cf0e204950e09e2ceefb2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e2bad1cf5d8d1ce8ad480d3b1ca4d45d156f9857324cf0e204950e09e2ceefb2","first_computed_at":"2026-05-17T23:46:13.947814Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:46:13.947814Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"w4cWlqT0byad93BZKbX5gk4OUHbTTucb69t3xTAmgJtn+WoyF5gojZBGTo2c7SxbCZrCl9v0KDRJIt5kGttzDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:46:13.948479Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.05644","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4f0a77c57fc8b237b3f3f791a9ad1293d501e09b5c893eda786e8fc53f18868d","sha256:00c2b892b0ff9d95639ae4bcc6baba9d10cb055039bb351a46a7bc512e2d9be9"],"state_sha256":"e0b63f37210925320236eb39d5337c0bc04213d14d234af62d7aec56857ef3a5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T/3ZLIU8bnlxmHFqnuPtKcC9rqkvH00AoN4CwZwBvGTFloRFAI5lOcbzSLyFwQyIUoDfHmccoM8l/AzTWoGNAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T12:55:55.300843Z","bundle_sha256":"17611b5c1607b7374b0d1c145bf667601b2becfaa9a0a9eb9f61826bd05370d2"}}