{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:STUIXS52I27NO5ZUUSK2IQSBKQ","short_pith_number":"pith:STUIXS52","canonical_record":{"source":{"id":"1508.01745","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-08-07T16:16:44Z","cross_cats_sorted":[],"title_canon_sha256":"fc1d5aae8091ce3d2d9e9584fc3ac4625b0ad1ce501a3428405f86de1f64dc89","abstract_canon_sha256":"08859a8926493fa035979dfc152d6e7b3460f46f5c03d90596b0c2c9759aaef5"},"schema_version":"1.0"},"canonical_sha256":"94e88bcbba46bed77734a495a4424154246d9bc09c478cb3fbc6e6a18d282392","source":{"kind":"arxiv","id":"1508.01745","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1508.01745","created_at":"2026-05-18T01:34:44Z"},{"alias_kind":"arxiv_version","alias_value":"1508.01745v2","created_at":"2026-05-18T01:34:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1508.01745","created_at":"2026-05-18T01:34:44Z"},{"alias_kind":"pith_short_12","alias_value":"STUIXS52I27N","created_at":"2026-05-18T12:29:42Z"},{"alias_kind":"pith_short_16","alias_value":"STUIXS52I27NO5ZU","created_at":"2026-05-18T12:29:42Z"},{"alias_kind":"pith_short_8","alias_value":"STUIXS52","created_at":"2026-05-18T12:29:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:STUIXS52I27NO5ZUUSK2IQSBKQ","target":"record","payload":{"canonical_record":{"source":{"id":"1508.01745","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-08-07T16:16:44Z","cross_cats_sorted":[],"title_canon_sha256":"fc1d5aae8091ce3d2d9e9584fc3ac4625b0ad1ce501a3428405f86de1f64dc89","abstract_canon_sha256":"08859a8926493fa035979dfc152d6e7b3460f46f5c03d90596b0c2c9759aaef5"},"schema_version":"1.0"},"canonical_sha256":"94e88bcbba46bed77734a495a4424154246d9bc09c478cb3fbc6e6a18d282392","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:34:44.883608Z","signature_b64":"x+IPaMoWpGWWzpuaNoCZL0zLnnBXwkHQDhhwXuOb6i+wy7xpcE8i6vVrB2pH6qN7xiCdS5IWpomteg3YFM6FAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94e88bcbba46bed77734a495a4424154246d9bc09c478cb3fbc6e6a18d282392","last_reissued_at":"2026-05-18T01:34:44.883153Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:34:44.883153Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1508.01745","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:34:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FLpViAS2UdjBtgPkwvctIkJRSzqML+T8W7qWtuG/hy6c0LTve+yQ06tsEUM325LbMwlafkHQ0e0UVKfPCgzhAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T02:39:15.287837Z"},"content_sha256":"d128deb7147307f9c0122a6ed4990733e5bb96e6df0442f8110967e10e5a9f42","schema_version":"1.0","event_id":"sha256:d128deb7147307f9c0122a6ed4990733e5bb96e6df0442f8110967e10e5a9f42"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:STUIXS52I27NO5ZUUSK2IQSBKQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"David Vandyke, Milica Gasic, Nikola Mrksic, Pei-Hao Su, Steve Young, Tsung-Hsien Wen","submitted_at":"2015-08-07T16:16:44Z","abstract_excerpt":"Natural language generation (NLG) is a critical component of spoken dialogue and it has a significant impact both on usability and perceived quality. Most NLG systems in common use employ rules and heuristics and tend to generate rigid and stylised responses without the natural variation of human language. They are also not easily scaled to systems covering multiple domains and languages. This paper presents a statistical language generator based on a semantically controlled Long Short-term Memory (LSTM) structure. The LSTM generator can learn from unaligned data by jointly optimising sentence"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1508.01745","kind":"arxiv","version":2},"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":"2026-05-18T01:34:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ThoJ3yMKTM3MIVEj20KJe+wygCB2SQm8/tBI4HQMvMQmKsnqAd/eY86PHmHsUuNLey7TCCC4MnQRuThwnackCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T02:39:15.288580Z"},"content_sha256":"90c5329b9a6ebf658b19376f2e0ee5ac42db04ec8ab5b7f749c7576d74953a07","schema_version":"1.0","event_id":"sha256:90c5329b9a6ebf658b19376f2e0ee5ac42db04ec8ab5b7f749c7576d74953a07"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/STUIXS52I27NO5ZUUSK2IQSBKQ/bundle.json","state_url":"https://pith.science/pith/STUIXS52I27NO5ZUUSK2IQSBKQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/STUIXS52I27NO5ZUUSK2IQSBKQ/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":"2026-05-20T02:39:15Z","links":{"resolver":"https://pith.science/pith/STUIXS52I27NO5ZUUSK2IQSBKQ","bundle":"https://pith.science/pith/STUIXS52I27NO5ZUUSK2IQSBKQ/bundle.json","state":"https://pith.science/pith/STUIXS52I27NO5ZUUSK2IQSBKQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/STUIXS52I27NO5ZUUSK2IQSBKQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:STUIXS52I27NO5ZUUSK2IQSBKQ","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":"08859a8926493fa035979dfc152d6e7b3460f46f5c03d90596b0c2c9759aaef5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-08-07T16:16:44Z","title_canon_sha256":"fc1d5aae8091ce3d2d9e9584fc3ac4625b0ad1ce501a3428405f86de1f64dc89"},"schema_version":"1.0","source":{"id":"1508.01745","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1508.01745","created_at":"2026-05-18T01:34:44Z"},{"alias_kind":"arxiv_version","alias_value":"1508.01745v2","created_at":"2026-05-18T01:34:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1508.01745","created_at":"2026-05-18T01:34:44Z"},{"alias_kind":"pith_short_12","alias_value":"STUIXS52I27N","created_at":"2026-05-18T12:29:42Z"},{"alias_kind":"pith_short_16","alias_value":"STUIXS52I27NO5ZU","created_at":"2026-05-18T12:29:42Z"},{"alias_kind":"pith_short_8","alias_value":"STUIXS52","created_at":"2026-05-18T12:29:42Z"}],"graph_snapshots":[{"event_id":"sha256:90c5329b9a6ebf658b19376f2e0ee5ac42db04ec8ab5b7f749c7576d74953a07","target":"graph","created_at":"2026-05-18T01:34:44Z","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":"Natural language generation (NLG) is a critical component of spoken dialogue and it has a significant impact both on usability and perceived quality. Most NLG systems in common use employ rules and heuristics and tend to generate rigid and stylised responses without the natural variation of human language. They are also not easily scaled to systems covering multiple domains and languages. This paper presents a statistical language generator based on a semantically controlled Long Short-term Memory (LSTM) structure. The LSTM generator can learn from unaligned data by jointly optimising sentence","authors_text":"David Vandyke, Milica Gasic, Nikola Mrksic, Pei-Hao Su, Steve Young, Tsung-Hsien Wen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-08-07T16:16:44Z","title":"Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1508.01745","kind":"arxiv","version":2},"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:d128deb7147307f9c0122a6ed4990733e5bb96e6df0442f8110967e10e5a9f42","target":"record","created_at":"2026-05-18T01:34:44Z","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":"08859a8926493fa035979dfc152d6e7b3460f46f5c03d90596b0c2c9759aaef5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-08-07T16:16:44Z","title_canon_sha256":"fc1d5aae8091ce3d2d9e9584fc3ac4625b0ad1ce501a3428405f86de1f64dc89"},"schema_version":"1.0","source":{"id":"1508.01745","kind":"arxiv","version":2}},"canonical_sha256":"94e88bcbba46bed77734a495a4424154246d9bc09c478cb3fbc6e6a18d282392","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"94e88bcbba46bed77734a495a4424154246d9bc09c478cb3fbc6e6a18d282392","first_computed_at":"2026-05-18T01:34:44.883153Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:34:44.883153Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"x+IPaMoWpGWWzpuaNoCZL0zLnnBXwkHQDhhwXuOb6i+wy7xpcE8i6vVrB2pH6qN7xiCdS5IWpomteg3YFM6FAA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:34:44.883608Z","signed_message":"canonical_sha256_bytes"},"source_id":"1508.01745","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d128deb7147307f9c0122a6ed4990733e5bb96e6df0442f8110967e10e5a9f42","sha256:90c5329b9a6ebf658b19376f2e0ee5ac42db04ec8ab5b7f749c7576d74953a07"],"state_sha256":"072c36e91076a02c3835e48fda4d9f4fc89fc246d4946f66b696fa90f5358781"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wlKei2LStCAfeCFyyVo2JGlT7g1jY4by/ALGt8NiZ0HqnMzP5/wKGpjmQuF5iMWMiGoZ257eNjevWQsmxQv6Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-20T02:39:15.292643Z","bundle_sha256":"0bbcdda6e9a5f0329aebfec40f513c6b3a7d7caf318a7332aa4ebf23d8b8d77f"}}