{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:ZDTW3ZE6OAMLXMCGP57ZID5AOK","short_pith_number":"pith:ZDTW3ZE6","canonical_record":{"source":{"id":"1909.06317","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-13T16:27:08Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"43bd93863c04c134517d4c3efc82bd6255a5eac30163fca2604fefbcd42db42c","abstract_canon_sha256":"721251feb5a5078c5741c611c3b48117e2785442bb206e79d321691ed378455c"},"schema_version":"1.0"},"canonical_sha256":"c8e76de49e7018bbb0467f7f940fa072a28a3b7eda8e957a81d91acbf39051d0","source":{"kind":"arxiv","id":"1909.06317","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.06317","created_at":"2026-07-05T02:47:38Z"},{"alias_kind":"arxiv_version","alias_value":"1909.06317v2","created_at":"2026-07-05T02:47:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.06317","created_at":"2026-07-05T02:47:38Z"},{"alias_kind":"pith_short_12","alias_value":"ZDTW3ZE6OAML","created_at":"2026-07-05T02:47:38Z"},{"alias_kind":"pith_short_16","alias_value":"ZDTW3ZE6OAMLXMCG","created_at":"2026-07-05T02:47:38Z"},{"alias_kind":"pith_short_8","alias_value":"ZDTW3ZE6","created_at":"2026-07-05T02:47:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:ZDTW3ZE6OAMLXMCGP57ZID5AOK","target":"record","payload":{"canonical_record":{"source":{"id":"1909.06317","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-13T16:27:08Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"43bd93863c04c134517d4c3efc82bd6255a5eac30163fca2604fefbcd42db42c","abstract_canon_sha256":"721251feb5a5078c5741c611c3b48117e2785442bb206e79d321691ed378455c"},"schema_version":"1.0"},"canonical_sha256":"c8e76de49e7018bbb0467f7f940fa072a28a3b7eda8e957a81d91acbf39051d0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:47:38.057244Z","signature_b64":"O+TjeMtGKTT2X88hFrh6rC8s61RpiBlYDA8Cptf7pkeCnr0GOy2XjXHqueBgWoMq7boDxh9r4ejGv4c4vOMjAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8e76de49e7018bbb0467f7f940fa072a28a3b7eda8e957a81d91acbf39051d0","last_reissued_at":"2026-07-05T02:47:38.056783Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:47:38.056783Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1909.06317","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":"2026-07-05T02:47:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zFo3PyIpI2L7v3BDoVrzhXjebho7R0YyIwDyPri0vW/uNMYbDiqOBodhqwit3UKwMlIexp48vwNYS0JVckZ8BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T03:13:59.325603Z"},"content_sha256":"c7d3dbde5d8c0bcb9d1f024159099671e95a64a63ce66a18d76352fe82f46dab","schema_version":"1.0","event_id":"sha256:c7d3dbde5d8c0bcb9d1f024159099671e95a64a63ce66a18d76352fe82f46dab"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:ZDTW3ZE6OAMLXMCGP57ZID5AOK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Comparative Study on Transformer vs RNN in Speech Applications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Hirofumi Inaguma, Masao Someki, Nanxin Chen, Nelson Enrique Yalta Soplin, Ryuichi Yamamoto, Shigeki Karita, Shinji Watanabe, Takaaki Hori, Takenori Yoshimura, Tomoki Hayashi, Wangyou Zhang, Xiaofei Wang, Ziyan Jiang","submitted_at":"2019-09-13T16:27:08Z","abstract_excerpt":"Sequence-to-sequence models have been widely used in end-to-end speech processing, for example, automatic speech recognition (ASR), speech translation (ST), and text-to-speech (TTS). This paper focuses on an emergent sequence-to-sequence model called Transformer, which achieves state-of-the-art performance in neural machine translation and other natural language processing applications. We undertook intensive studies in which we experimentally compared and analyzed Transformer and conventional recurrent neural networks (RNN) in a total of 15 ASR, one multilingual ASR, one ST, and two TTS bench"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.06317","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1909.06317/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":"2026-07-05T02:47:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3oIvcynzsoxeWUL1483HpZVB4pq6F01pqMlF44mBarj7wt37G6CQPCicZ4fSpeUVeeXXBUunEjwmUc91iqVBCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T03:13:59.326107Z"},"content_sha256":"f2e921bcb072223b25cfa0ceb4f64ef1cd1a3104a88e4a167469fa767181eb7e","schema_version":"1.0","event_id":"sha256:f2e921bcb072223b25cfa0ceb4f64ef1cd1a3104a88e4a167469fa767181eb7e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZDTW3ZE6OAMLXMCGP57ZID5AOK/bundle.json","state_url":"https://pith.science/pith/ZDTW3ZE6OAMLXMCGP57ZID5AOK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZDTW3ZE6OAMLXMCGP57ZID5AOK/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":"2026-08-04T03:13:59Z","links":{"resolver":"https://pith.science/pith/ZDTW3ZE6OAMLXMCGP57ZID5AOK","bundle":"https://pith.science/pith/ZDTW3ZE6OAMLXMCGP57ZID5AOK/bundle.json","state":"https://pith.science/pith/ZDTW3ZE6OAMLXMCGP57ZID5AOK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZDTW3ZE6OAMLXMCGP57ZID5AOK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:ZDTW3ZE6OAMLXMCGP57ZID5AOK","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":"721251feb5a5078c5741c611c3b48117e2785442bb206e79d321691ed378455c","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-13T16:27:08Z","title_canon_sha256":"43bd93863c04c134517d4c3efc82bd6255a5eac30163fca2604fefbcd42db42c"},"schema_version":"1.0","source":{"id":"1909.06317","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.06317","created_at":"2026-07-05T02:47:38Z"},{"alias_kind":"arxiv_version","alias_value":"1909.06317v2","created_at":"2026-07-05T02:47:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.06317","created_at":"2026-07-05T02:47:38Z"},{"alias_kind":"pith_short_12","alias_value":"ZDTW3ZE6OAML","created_at":"2026-07-05T02:47:38Z"},{"alias_kind":"pith_short_16","alias_value":"ZDTW3ZE6OAMLXMCG","created_at":"2026-07-05T02:47:38Z"},{"alias_kind":"pith_short_8","alias_value":"ZDTW3ZE6","created_at":"2026-07-05T02:47:38Z"}],"graph_snapshots":[{"event_id":"sha256:f2e921bcb072223b25cfa0ceb4f64ef1cd1a3104a88e4a167469fa767181eb7e","target":"graph","created_at":"2026-07-05T02:47:38Z","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/1909.06317/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sequence-to-sequence models have been widely used in end-to-end speech processing, for example, automatic speech recognition (ASR), speech translation (ST), and text-to-speech (TTS). This paper focuses on an emergent sequence-to-sequence model called Transformer, which achieves state-of-the-art performance in neural machine translation and other natural language processing applications. We undertook intensive studies in which we experimentally compared and analyzed Transformer and conventional recurrent neural networks (RNN) in a total of 15 ASR, one multilingual ASR, one ST, and two TTS bench","authors_text":"Hirofumi Inaguma, Masao Someki, Nanxin Chen, Nelson Enrique Yalta Soplin, Ryuichi Yamamoto, Shigeki Karita, Shinji Watanabe, Takaaki Hori, Takenori Yoshimura, Tomoki Hayashi, Wangyou Zhang, Xiaofei Wang, Ziyan Jiang","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-13T16:27:08Z","title":"A Comparative Study on Transformer vs RNN in Speech Applications"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.06317","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:c7d3dbde5d8c0bcb9d1f024159099671e95a64a63ce66a18d76352fe82f46dab","target":"record","created_at":"2026-07-05T02:47:38Z","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":"721251feb5a5078c5741c611c3b48117e2785442bb206e79d321691ed378455c","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-13T16:27:08Z","title_canon_sha256":"43bd93863c04c134517d4c3efc82bd6255a5eac30163fca2604fefbcd42db42c"},"schema_version":"1.0","source":{"id":"1909.06317","kind":"arxiv","version":2}},"canonical_sha256":"c8e76de49e7018bbb0467f7f940fa072a28a3b7eda8e957a81d91acbf39051d0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c8e76de49e7018bbb0467f7f940fa072a28a3b7eda8e957a81d91acbf39051d0","first_computed_at":"2026-07-05T02:47:38.056783Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:47:38.056783Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"O+TjeMtGKTT2X88hFrh6rC8s61RpiBlYDA8Cptf7pkeCnr0GOy2XjXHqueBgWoMq7boDxh9r4ejGv4c4vOMjAw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:47:38.057244Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.06317","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c7d3dbde5d8c0bcb9d1f024159099671e95a64a63ce66a18d76352fe82f46dab","sha256:f2e921bcb072223b25cfa0ceb4f64ef1cd1a3104a88e4a167469fa767181eb7e"],"state_sha256":"e4736b3f70dbb6f666f31d9bc9656393a13efee80de5ca1e7afcfa96a6bc45b2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Kc4kNIiibQtQlGvhmQswpg4wS0vhDy36R9si81On62p+kpWI1UZ+XBOp+goMvcopgr94GJawzqNDDNBsiCy5AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T03:13:59.329778Z","bundle_sha256":"47bfa1b379fe7bb68a149623329391997363af96e5e1b498d293cf42b9b0679f"}}