{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:PXHNLCVF3XYF5XHE7FBWHP5WGK","short_pith_number":"pith:PXHNLCVF","canonical_record":{"source":{"id":"1601.02539","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2016-01-11T17:54:53Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"c3c70002ea2fdf32d4f22e7320cce8088cee3741ba7624aa77b7743fe11a879c","abstract_canon_sha256":"9c64281a5bc6be6de33865094b62aadd2e7e1fb408742afb278775ede2518bf0"},"schema_version":"1.0"},"canonical_sha256":"7dced58aa5ddf05edce4f94363bfb632b27f3a92b31acdf1496996d6bf6ba5cd","source":{"kind":"arxiv","id":"1601.02539","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1601.02539","created_at":"2026-05-18T01:23:04Z"},{"alias_kind":"arxiv_version","alias_value":"1601.02539v1","created_at":"2026-05-18T01:23:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1601.02539","created_at":"2026-05-18T01:23:04Z"},{"alias_kind":"pith_short_12","alias_value":"PXHNLCVF3XYF","created_at":"2026-05-18T12:30:39Z"},{"alias_kind":"pith_short_16","alias_value":"PXHNLCVF3XYF5XHE","created_at":"2026-05-18T12:30:39Z"},{"alias_kind":"pith_short_8","alias_value":"PXHNLCVF","created_at":"2026-05-18T12:30:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:PXHNLCVF3XYF5XHE7FBWHP5WGK","target":"record","payload":{"canonical_record":{"source":{"id":"1601.02539","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2016-01-11T17:54:53Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"c3c70002ea2fdf32d4f22e7320cce8088cee3741ba7624aa77b7743fe11a879c","abstract_canon_sha256":"9c64281a5bc6be6de33865094b62aadd2e7e1fb408742afb278775ede2518bf0"},"schema_version":"1.0"},"canonical_sha256":"7dced58aa5ddf05edce4f94363bfb632b27f3a92b31acdf1496996d6bf6ba5cd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:23:04.893701Z","signature_b64":"1DcUNlvCt6fLdu4arwk3P6euIQePnKLtH10fMEfzXFMpR1N6ihHGyNixHGOcc5VpifMfLQiMsfAy2k//haEqAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7dced58aa5ddf05edce4f94363bfb632b27f3a92b31acdf1496996d6bf6ba5cd","last_reissued_at":"2026-05-18T01:23:04.893254Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:23:04.893254Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1601.02539","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":"2026-05-18T01:23:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pDSS61yyoNA8dZ4StsoDPDIeFtjxLtn9EWyJ9wwZjz4GBU+Jr/wdH1LuV2ofSKbxHJCU8Gopw2H/nGzCbL0qBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T20:08:45.755053Z"},"content_sha256":"91cc56886e27a8956a000435c3924f9d9f86c19cd8a744e5f19db333111a4a68","schema_version":"1.0","event_id":"sha256:91cc56886e27a8956a000435c3924f9d9f86c19cd8a744e5f19db333111a4a68"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:PXHNLCVF3XYF5XHE7FBWHP5WGK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Investigating gated recurrent neural networks for speech synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.CL","authors_text":"Simon King, Zhizheng Wu","submitted_at":"2016-01-11T17:54:53Z","abstract_excerpt":"Recently, recurrent neural networks (RNNs) as powerful sequence models have re-emerged as a potential acoustic model for statistical parametric speech synthesis (SPSS). The long short-term memory (LSTM) architecture is particularly attractive because it addresses the vanishing gradient problem in standard RNNs, making them easier to train. Although recent studies have demonstrated that LSTMs can achieve significantly better performance on SPSS than deep feed-forward neural networks, little is known about why. Here we attempt to answer two questions: a) why do LSTMs work well as a sequence mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1601.02539","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":"2026-05-18T01:23:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r6ENFxlANUxlV1GndTRd6NELNljEFK8GRSWjYA62OC63fUn08wiUZQ5RiVCHGtB/lT3wDOa46GH0Cui+I10dDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T20:08:45.755533Z"},"content_sha256":"2c992a8150e896ab2abb317c0bfcf2008c49b358bf5d27e4d74a66d887c3476f","schema_version":"1.0","event_id":"sha256:2c992a8150e896ab2abb317c0bfcf2008c49b358bf5d27e4d74a66d887c3476f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PXHNLCVF3XYF5XHE7FBWHP5WGK/bundle.json","state_url":"https://pith.science/pith/PXHNLCVF3XYF5XHE7FBWHP5WGK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PXHNLCVF3XYF5XHE7FBWHP5WGK/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":"2026-05-31T20:08:45Z","links":{"resolver":"https://pith.science/pith/PXHNLCVF3XYF5XHE7FBWHP5WGK","bundle":"https://pith.science/pith/PXHNLCVF3XYF5XHE7FBWHP5WGK/bundle.json","state":"https://pith.science/pith/PXHNLCVF3XYF5XHE7FBWHP5WGK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PXHNLCVF3XYF5XHE7FBWHP5WGK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:PXHNLCVF3XYF5XHE7FBWHP5WGK","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":"9c64281a5bc6be6de33865094b62aadd2e7e1fb408742afb278775ede2518bf0","cross_cats_sorted":["cs.NE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2016-01-11T17:54:53Z","title_canon_sha256":"c3c70002ea2fdf32d4f22e7320cce8088cee3741ba7624aa77b7743fe11a879c"},"schema_version":"1.0","source":{"id":"1601.02539","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1601.02539","created_at":"2026-05-18T01:23:04Z"},{"alias_kind":"arxiv_version","alias_value":"1601.02539v1","created_at":"2026-05-18T01:23:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1601.02539","created_at":"2026-05-18T01:23:04Z"},{"alias_kind":"pith_short_12","alias_value":"PXHNLCVF3XYF","created_at":"2026-05-18T12:30:39Z"},{"alias_kind":"pith_short_16","alias_value":"PXHNLCVF3XYF5XHE","created_at":"2026-05-18T12:30:39Z"},{"alias_kind":"pith_short_8","alias_value":"PXHNLCVF","created_at":"2026-05-18T12:30:39Z"}],"graph_snapshots":[{"event_id":"sha256:2c992a8150e896ab2abb317c0bfcf2008c49b358bf5d27e4d74a66d887c3476f","target":"graph","created_at":"2026-05-18T01:23:04Z","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":"Recently, recurrent neural networks (RNNs) as powerful sequence models have re-emerged as a potential acoustic model for statistical parametric speech synthesis (SPSS). The long short-term memory (LSTM) architecture is particularly attractive because it addresses the vanishing gradient problem in standard RNNs, making them easier to train. Although recent studies have demonstrated that LSTMs can achieve significantly better performance on SPSS than deep feed-forward neural networks, little is known about why. Here we attempt to answer two questions: a) why do LSTMs work well as a sequence mode","authors_text":"Simon King, Zhizheng Wu","cross_cats":["cs.NE"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2016-01-11T17:54:53Z","title":"Investigating gated recurrent neural networks for speech synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1601.02539","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":"sha256:91cc56886e27a8956a000435c3924f9d9f86c19cd8a744e5f19db333111a4a68","target":"record","created_at":"2026-05-18T01:23:04Z","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":"9c64281a5bc6be6de33865094b62aadd2e7e1fb408742afb278775ede2518bf0","cross_cats_sorted":["cs.NE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2016-01-11T17:54:53Z","title_canon_sha256":"c3c70002ea2fdf32d4f22e7320cce8088cee3741ba7624aa77b7743fe11a879c"},"schema_version":"1.0","source":{"id":"1601.02539","kind":"arxiv","version":1}},"canonical_sha256":"7dced58aa5ddf05edce4f94363bfb632b27f3a92b31acdf1496996d6bf6ba5cd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7dced58aa5ddf05edce4f94363bfb632b27f3a92b31acdf1496996d6bf6ba5cd","first_computed_at":"2026-05-18T01:23:04.893254Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:23:04.893254Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1DcUNlvCt6fLdu4arwk3P6euIQePnKLtH10fMEfzXFMpR1N6ihHGyNixHGOcc5VpifMfLQiMsfAy2k//haEqAw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:23:04.893701Z","signed_message":"canonical_sha256_bytes"},"source_id":"1601.02539","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:91cc56886e27a8956a000435c3924f9d9f86c19cd8a744e5f19db333111a4a68","sha256:2c992a8150e896ab2abb317c0bfcf2008c49b358bf5d27e4d74a66d887c3476f"],"state_sha256":"708d924e4ce8d0bcd28d128dc8dabed67989906d5eb04e4ef84bd0aa9c4b03ff"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PdsYcXCXvfC5iCRttjxjm9sYGfxWtBGh3yxzhD8dQs1UpTUAhN8nIZQ+T8t4xVh0edmImgad0Z3syrmH298dDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T20:08:45.758557Z","bundle_sha256":"9ea8c62b427cbc6f5e6c746110ca19e7f60498e06be4d67a05076444dbab389c"}}