{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:2S5WXAV5J5JFHARFHWRK4Z2TCE","short_pith_number":"pith:2S5WXAV5","canonical_record":{"source":{"id":"1904.09521","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-21T00:42:22Z","cross_cats_sorted":[],"title_canon_sha256":"ad80dca48f679b99b1008d0dc241e1a3d9e6ae5d054422832cd1285ad30ecaf4","abstract_canon_sha256":"95dbba7aef074a0aced9d8c69d48a340d13f8229b0151ad74ab42914159ea049"},"schema_version":"1.0"},"canonical_sha256":"d4bb6b82bd4f525382253da2ae67531114e5d1d6367be79a51d2e5e29bcda6a7","source":{"kind":"arxiv","id":"1904.09521","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.09521","created_at":"2026-07-05T00:55:56Z"},{"alias_kind":"arxiv_version","alias_value":"1904.09521v3","created_at":"2026-07-05T00:55:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.09521","created_at":"2026-07-05T00:55:56Z"},{"alias_kind":"pith_short_12","alias_value":"2S5WXAV5J5JF","created_at":"2026-07-05T00:55:56Z"},{"alias_kind":"pith_short_16","alias_value":"2S5WXAV5J5JFHARF","created_at":"2026-07-05T00:55:56Z"},{"alias_kind":"pith_short_8","alias_value":"2S5WXAV5","created_at":"2026-07-05T00:55:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:2S5WXAV5J5JFHARFHWRK4Z2TCE","target":"record","payload":{"canonical_record":{"source":{"id":"1904.09521","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-21T00:42:22Z","cross_cats_sorted":[],"title_canon_sha256":"ad80dca48f679b99b1008d0dc241e1a3d9e6ae5d054422832cd1285ad30ecaf4","abstract_canon_sha256":"95dbba7aef074a0aced9d8c69d48a340d13f8229b0151ad74ab42914159ea049"},"schema_version":"1.0"},"canonical_sha256":"d4bb6b82bd4f525382253da2ae67531114e5d1d6367be79a51d2e5e29bcda6a7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:55:56.941274Z","signature_b64":"z+ihCL7HtFrMaudBMigyAhRtx9cpfMmE5cTi2BsiIgfZuzOQvmrLl1hU1hj9r7r9Ko3bH45H20DKmf63i1V3CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d4bb6b82bd4f525382253da2ae67531114e5d1d6367be79a51d2e5e29bcda6a7","last_reissued_at":"2026-07-05T00:55:56.940766Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:55:56.940766Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1904.09521","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:55:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TLoYFsgpsGzQq3ca46+Ox6jkPWm65my5h9iCQzT8U8kLNvKGXE9mmjfb29D00/narEpXna0QjRPwSFkBeULcDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T14:14:15.664880Z"},"content_sha256":"7d85723791e78294c4ce859627252ec8a2f3028b4fe38d1401f7371a8c1ec5ad","schema_version":"1.0","event_id":"sha256:7d85723791e78294c4ce859627252ec8a2f3028b4fe38d1401f7371a8c1ec5ad"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:2S5WXAV5J5JFHARFHWRK4Z2TCE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Few-Shot NLG with Pre-Trained Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Harini Eavani, Wenhu Chen, William Yang Wang, Yinyin Liu, Zhiyu Chen","submitted_at":"2019-04-21T00:42:22Z","abstract_excerpt":"Neural-based end-to-end approaches to natural language generation (NLG) from structured data or knowledge are data-hungry, making their adoption for real-world applications difficult with limited data. In this work, we propose the new task of \\textit{few-shot natural language generation}. Motivated by how humans tend to summarize tabular data, we propose a simple yet effective approach and show that it not only demonstrates strong performance but also provides good generalization across domains. The design of the model architecture is based on two aspects: content selection from input data and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.09521","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1904.09521/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T00:55:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wKoUKVMTePqcZwPzKd0SCzINDNssXARXtLfFGUACqyvlJpQL4Q19nfhLS6HSsVsmUFrfyYbQjyctpS++RSk/Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T14:14:15.665485Z"},"content_sha256":"feb578879dd70f6acbc50fe571a8641eee6ec599cacd8087a20f44b8a23a3c6c","schema_version":"1.0","event_id":"sha256:feb578879dd70f6acbc50fe571a8641eee6ec599cacd8087a20f44b8a23a3c6c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2S5WXAV5J5JFHARFHWRK4Z2TCE/bundle.json","state_url":"https://pith.science/pith/2S5WXAV5J5JFHARFHWRK4Z2TCE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2S5WXAV5J5JFHARFHWRK4Z2TCE/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":"2026-08-08T14:14:15Z","links":{"resolver":"https://pith.science/pith/2S5WXAV5J5JFHARFHWRK4Z2TCE","bundle":"https://pith.science/pith/2S5WXAV5J5JFHARFHWRK4Z2TCE/bundle.json","state":"https://pith.science/pith/2S5WXAV5J5JFHARFHWRK4Z2TCE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2S5WXAV5J5JFHARFHWRK4Z2TCE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:2S5WXAV5J5JFHARFHWRK4Z2TCE","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":"95dbba7aef074a0aced9d8c69d48a340d13f8229b0151ad74ab42914159ea049","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-21T00:42:22Z","title_canon_sha256":"ad80dca48f679b99b1008d0dc241e1a3d9e6ae5d054422832cd1285ad30ecaf4"},"schema_version":"1.0","source":{"id":"1904.09521","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.09521","created_at":"2026-07-05T00:55:56Z"},{"alias_kind":"arxiv_version","alias_value":"1904.09521v3","created_at":"2026-07-05T00:55:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.09521","created_at":"2026-07-05T00:55:56Z"},{"alias_kind":"pith_short_12","alias_value":"2S5WXAV5J5JF","created_at":"2026-07-05T00:55:56Z"},{"alias_kind":"pith_short_16","alias_value":"2S5WXAV5J5JFHARF","created_at":"2026-07-05T00:55:56Z"},{"alias_kind":"pith_short_8","alias_value":"2S5WXAV5","created_at":"2026-07-05T00:55:56Z"}],"graph_snapshots":[{"event_id":"sha256:feb578879dd70f6acbc50fe571a8641eee6ec599cacd8087a20f44b8a23a3c6c","target":"graph","created_at":"2026-07-05T00:55:56Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1904.09521/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Neural-based end-to-end approaches to natural language generation (NLG) from structured data or knowledge are data-hungry, making their adoption for real-world applications difficult with limited data. In this work, we propose the new task of \\textit{few-shot natural language generation}. Motivated by how humans tend to summarize tabular data, we propose a simple yet effective approach and show that it not only demonstrates strong performance but also provides good generalization across domains. The design of the model architecture is based on two aspects: content selection from input data and","authors_text":"Harini Eavani, Wenhu Chen, William Yang Wang, Yinyin Liu, Zhiyu Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-21T00:42:22Z","title":"Few-Shot NLG with Pre-Trained Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.09521","kind":"arxiv","version":3},"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":"sha256:7d85723791e78294c4ce859627252ec8a2f3028b4fe38d1401f7371a8c1ec5ad","target":"record","created_at":"2026-07-05T00:55:56Z","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":"95dbba7aef074a0aced9d8c69d48a340d13f8229b0151ad74ab42914159ea049","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-21T00:42:22Z","title_canon_sha256":"ad80dca48f679b99b1008d0dc241e1a3d9e6ae5d054422832cd1285ad30ecaf4"},"schema_version":"1.0","source":{"id":"1904.09521","kind":"arxiv","version":3}},"canonical_sha256":"d4bb6b82bd4f525382253da2ae67531114e5d1d6367be79a51d2e5e29bcda6a7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d4bb6b82bd4f525382253da2ae67531114e5d1d6367be79a51d2e5e29bcda6a7","first_computed_at":"2026-07-05T00:55:56.940766Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:55:56.940766Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"z+ihCL7HtFrMaudBMigyAhRtx9cpfMmE5cTi2BsiIgfZuzOQvmrLl1hU1hj9r7r9Ko3bH45H20DKmf63i1V3CA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:55:56.941274Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.09521","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7d85723791e78294c4ce859627252ec8a2f3028b4fe38d1401f7371a8c1ec5ad","sha256:feb578879dd70f6acbc50fe571a8641eee6ec599cacd8087a20f44b8a23a3c6c"],"state_sha256":"92033bc57caa846283c58ab3e06cb908fd5dc06f3e92559473d94ba3ce7ee488"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r2Ait/mcxTb6MRPJYk9yQhhR8rERFlSdjXrwGhoppFUi1fZSp6lQqJRErkrTZjg196dCcPx98w0bHS+eeXMnDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T14:14:15.672134Z","bundle_sha256":"1b10d1af3d304abb451ecfb132a50ab875e1c32ff38167abee91baaa7b2c4476"}}