{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:XFVJCWQ6ER2UYSTSTACMYIPVV5","short_pith_number":"pith:XFVJCWQ6","canonical_record":{"source":{"id":"1808.10122","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-30T05:15:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9fb0a42b69eb1dbfcdcaa4dffb0ff9c642e5fc4a9ac44ede843b8b2fae7b6e0b","abstract_canon_sha256":"506f417ad5de63bb794d22dd9187a9f0dcc533d27627ef982170433d9c787548"},"schema_version":"1.0"},"canonical_sha256":"b96a915a1e24754c4a729804cc21f5af53f2735ace97aec73e45eb49416654da","source":{"kind":"arxiv","id":"1808.10122","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.10122","created_at":"2026-05-17T23:43:17Z"},{"alias_kind":"arxiv_version","alias_value":"1808.10122v3","created_at":"2026-05-17T23:43:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.10122","created_at":"2026-05-17T23:43:17Z"},{"alias_kind":"pith_short_12","alias_value":"XFVJCWQ6ER2U","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"XFVJCWQ6ER2UYSTS","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"XFVJCWQ6","created_at":"2026-05-18T12:33:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:XFVJCWQ6ER2UYSTSTACMYIPVV5","target":"record","payload":{"canonical_record":{"source":{"id":"1808.10122","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-30T05:15:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9fb0a42b69eb1dbfcdcaa4dffb0ff9c642e5fc4a9ac44ede843b8b2fae7b6e0b","abstract_canon_sha256":"506f417ad5de63bb794d22dd9187a9f0dcc533d27627ef982170433d9c787548"},"schema_version":"1.0"},"canonical_sha256":"b96a915a1e24754c4a729804cc21f5af53f2735ace97aec73e45eb49416654da","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:17.590432Z","signature_b64":"0k37QWZEhC1G1tjcUjg3eC/pIoLkceeNL0/EseTXy5yKCklk4rxyPxksWBbA1xAMDllkU77zS6/t8UFi2qNnDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b96a915a1e24754c4a729804cc21f5af53f2735ace97aec73e45eb49416654da","last_reissued_at":"2026-05-17T23:43:17.589819Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:17.589819Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1808.10122","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":"2026-05-17T23:43:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qUdr7w1HzYwtStAoZgLNjY62pfV0bAtuCDWAr77d1w63D42hFFNa+gO6WgBRu4ShlNKMN+yQWI/0nSHYubkPDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T22:55:10.230249Z"},"content_sha256":"9f9ab0410ba776e6f631da364bc5eb94bc65df94ef3bce5bdc2284e05304ceaf","schema_version":"1.0","event_id":"sha256:9f9ab0410ba776e6f631da364bc5eb94bc65df94ef3bce5bdc2284e05304ceaf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:XFVJCWQ6ER2UYSTSTACMYIPVV5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Neural Templates for Text Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Alexander M. Rush, Sam Wiseman, Stuart M. Shieber","submitted_at":"2018-08-30T05:15:42Z","abstract_excerpt":"While neural, encoder-decoder models have had significant empirical success in text generation, there remain several unaddressed problems with this style of generation. Encoder-decoder models are largely (a) uninterpretable, and (b) difficult to control in terms of their phrasing or content. This work proposes a neural generation system using a hidden semi-markov model (HSMM) decoder, which learns latent, discrete templates jointly with learning to generate. We show that this model learns useful templates, and that these templates make generation both more interpretable and controllable. Furth"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.10122","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":""},"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":"2026-05-17T23:43:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"75fI1u8OTEVSm/H0ISEQIMHEbL7lHyoJy3i18LxLnKZV0r+4CZ+g7J6Ua5gcSDLZaawp3yccGMCBsZPYctLqBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T22:55:10.230635Z"},"content_sha256":"ee65a94dc90866324609fd1d69a8fa08e6e27234a8c93358035cb15bc48ab5cb","schema_version":"1.0","event_id":"sha256:ee65a94dc90866324609fd1d69a8fa08e6e27234a8c93358035cb15bc48ab5cb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XFVJCWQ6ER2UYSTSTACMYIPVV5/bundle.json","state_url":"https://pith.science/pith/XFVJCWQ6ER2UYSTSTACMYIPVV5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XFVJCWQ6ER2UYSTSTACMYIPVV5/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":"2026-06-02T22:55:10Z","links":{"resolver":"https://pith.science/pith/XFVJCWQ6ER2UYSTSTACMYIPVV5","bundle":"https://pith.science/pith/XFVJCWQ6ER2UYSTSTACMYIPVV5/bundle.json","state":"https://pith.science/pith/XFVJCWQ6ER2UYSTSTACMYIPVV5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XFVJCWQ6ER2UYSTSTACMYIPVV5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:XFVJCWQ6ER2UYSTSTACMYIPVV5","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":"506f417ad5de63bb794d22dd9187a9f0dcc533d27627ef982170433d9c787548","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-30T05:15:42Z","title_canon_sha256":"9fb0a42b69eb1dbfcdcaa4dffb0ff9c642e5fc4a9ac44ede843b8b2fae7b6e0b"},"schema_version":"1.0","source":{"id":"1808.10122","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.10122","created_at":"2026-05-17T23:43:17Z"},{"alias_kind":"arxiv_version","alias_value":"1808.10122v3","created_at":"2026-05-17T23:43:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.10122","created_at":"2026-05-17T23:43:17Z"},{"alias_kind":"pith_short_12","alias_value":"XFVJCWQ6ER2U","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"XFVJCWQ6ER2UYSTS","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"XFVJCWQ6","created_at":"2026-05-18T12:33:01Z"}],"graph_snapshots":[{"event_id":"sha256:ee65a94dc90866324609fd1d69a8fa08e6e27234a8c93358035cb15bc48ab5cb","target":"graph","created_at":"2026-05-17T23:43:17Z","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":"While neural, encoder-decoder models have had significant empirical success in text generation, there remain several unaddressed problems with this style of generation. Encoder-decoder models are largely (a) uninterpretable, and (b) difficult to control in terms of their phrasing or content. This work proposes a neural generation system using a hidden semi-markov model (HSMM) decoder, which learns latent, discrete templates jointly with learning to generate. We show that this model learns useful templates, and that these templates make generation both more interpretable and controllable. Furth","authors_text":"Alexander M. Rush, Sam Wiseman, Stuart M. Shieber","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-30T05:15:42Z","title":"Learning Neural Templates for Text Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.10122","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":"sha256:9f9ab0410ba776e6f631da364bc5eb94bc65df94ef3bce5bdc2284e05304ceaf","target":"record","created_at":"2026-05-17T23:43:17Z","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":"506f417ad5de63bb794d22dd9187a9f0dcc533d27627ef982170433d9c787548","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-30T05:15:42Z","title_canon_sha256":"9fb0a42b69eb1dbfcdcaa4dffb0ff9c642e5fc4a9ac44ede843b8b2fae7b6e0b"},"schema_version":"1.0","source":{"id":"1808.10122","kind":"arxiv","version":3}},"canonical_sha256":"b96a915a1e24754c4a729804cc21f5af53f2735ace97aec73e45eb49416654da","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b96a915a1e24754c4a729804cc21f5af53f2735ace97aec73e45eb49416654da","first_computed_at":"2026-05-17T23:43:17.589819Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:43:17.589819Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0k37QWZEhC1G1tjcUjg3eC/pIoLkceeNL0/EseTXy5yKCklk4rxyPxksWBbA1xAMDllkU77zS6/t8UFi2qNnDw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:43:17.590432Z","signed_message":"canonical_sha256_bytes"},"source_id":"1808.10122","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9f9ab0410ba776e6f631da364bc5eb94bc65df94ef3bce5bdc2284e05304ceaf","sha256:ee65a94dc90866324609fd1d69a8fa08e6e27234a8c93358035cb15bc48ab5cb"],"state_sha256":"d16d2faace374b66cfd626a72cb67589d499f52959eed7137e3211a138cda08d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VPdX60IVX5PZKvpqBdmBbaKnu5PlZs/rVNa2KeX/KcLlEwIiiFsn2tx+qoByz9D8BTHtMON1L/LsyNVDANcYAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T22:55:10.232611Z","bundle_sha256":"ded358f74d0f666d4e77260fd642170c6015ea8ad4790a57204589516afacdb1"}}