{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:MUAZJ5HCYE4Z6RGYJYHB5AEPLS","short_pith_number":"pith:MUAZJ5HC","canonical_record":{"source":{"id":"2107.05382","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-07-07T12:52:49Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"6989cba20519d18db8d4b38a447f5f5def14c738f59df39d148d1bd898c9f913","abstract_canon_sha256":"20015f17bd0989ca3000392b51ab3017024c273cf103fa84aa66c3a17544c7de"},"schema_version":"1.0"},"canonical_sha256":"650194f4e2c1399f44d84e0e1e808f5c84c21a80846ee5e212f4af0062587680","source":{"kind":"arxiv","id":"2107.05382","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.05382","created_at":"2026-07-05T02:57:02Z"},{"alias_kind":"arxiv_version","alias_value":"2107.05382v1","created_at":"2026-07-05T02:57:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.05382","created_at":"2026-07-05T02:57:02Z"},{"alias_kind":"pith_short_12","alias_value":"MUAZJ5HCYE4Z","created_at":"2026-07-05T02:57:02Z"},{"alias_kind":"pith_short_16","alias_value":"MUAZJ5HCYE4Z6RGY","created_at":"2026-07-05T02:57:02Z"},{"alias_kind":"pith_short_8","alias_value":"MUAZJ5HC","created_at":"2026-07-05T02:57:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:MUAZJ5HCYE4Z6RGYJYHB5AEPLS","target":"record","payload":{"canonical_record":{"source":{"id":"2107.05382","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-07-07T12:52:49Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"6989cba20519d18db8d4b38a447f5f5def14c738f59df39d148d1bd898c9f913","abstract_canon_sha256":"20015f17bd0989ca3000392b51ab3017024c273cf103fa84aa66c3a17544c7de"},"schema_version":"1.0"},"canonical_sha256":"650194f4e2c1399f44d84e0e1e808f5c84c21a80846ee5e212f4af0062587680","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:57:02.292552Z","signature_b64":"5/ZekyO66R+EaLThRxy+pX8Jj4rptTV0wstxGH2yrbbRn+a2nqAQnhsJmdNDjm/WKidPnQQ7dvU9hTlmTgX/Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"650194f4e2c1399f44d84e0e1e808f5c84c21a80846ee5e212f4af0062587680","last_reissued_at":"2026-07-05T02:57:02.292127Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:57:02.292127Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2107.05382","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":"2026-07-05T02:57:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bpI0mpyE992dCmATiDe5FsD6slH8n8YsXzdMuAXnQv/ooOiRSpoOogPLiya9TrZK/Gx1G5g69XtPLwEvfLy3Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T06:19:43.019932Z"},"content_sha256":"536a1b66ac93f3b761adbe418245241dc6eca626b45912022c46c74abb0c4f49","schema_version":"1.0","event_id":"sha256:536a1b66ac93f3b761adbe418245241dc6eca626b45912022c46c74abb0c4f49"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:MUAZJ5HCYE4Z6RGYJYHB5AEPLS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"End-to-End Rich Transcription-Style Automatic Speech Recognition with Semi-Supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Akihiko Takashima, Mana Ihori, Naoki Makishima, Ryo Masumura, Shota Orihashi, Tomohiro Tanaka","submitted_at":"2021-07-07T12:52:49Z","abstract_excerpt":"We propose a semi-supervised learning method for building end-to-end rich transcription-style automatic speech recognition (RT-ASR) systems from small-scale rich transcription-style and large-scale common transcription-style datasets. In spontaneous speech tasks, various speech phenomena such as fillers, word fragments, laughter and coughs, etc. are often included. While common transcriptions do not give special awareness to these phenomena, rich transcriptions explicitly convert them into special phenomenon tokens as well as textual tokens. In previous studies, the textual and phenomenon toke"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.05382","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2107.05382/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":"2026-07-05T02:57:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e8HCAIPlYCC0Mmuf/Zue82fS4+MTT93QrB8ttFWVkT7XM8GmmW5lPTg8Gcfk8p/UAmwtxP6ACEfGG9Vs+Af3CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T06:19:43.020418Z"},"content_sha256":"0d81b1e33bebb93086e9304f4d0a4c69831fff75cf44a646c60f6573fae43506","schema_version":"1.0","event_id":"sha256:0d81b1e33bebb93086e9304f4d0a4c69831fff75cf44a646c60f6573fae43506"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MUAZJ5HCYE4Z6RGYJYHB5AEPLS/bundle.json","state_url":"https://pith.science/pith/MUAZJ5HCYE4Z6RGYJYHB5AEPLS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MUAZJ5HCYE4Z6RGYJYHB5AEPLS/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":"2026-08-07T06:19:43Z","links":{"resolver":"https://pith.science/pith/MUAZJ5HCYE4Z6RGYJYHB5AEPLS","bundle":"https://pith.science/pith/MUAZJ5HCYE4Z6RGYJYHB5AEPLS/bundle.json","state":"https://pith.science/pith/MUAZJ5HCYE4Z6RGYJYHB5AEPLS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MUAZJ5HCYE4Z6RGYJYHB5AEPLS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:MUAZJ5HCYE4Z6RGYJYHB5AEPLS","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":"20015f17bd0989ca3000392b51ab3017024c273cf103fa84aa66c3a17544c7de","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-07-07T12:52:49Z","title_canon_sha256":"6989cba20519d18db8d4b38a447f5f5def14c738f59df39d148d1bd898c9f913"},"schema_version":"1.0","source":{"id":"2107.05382","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.05382","created_at":"2026-07-05T02:57:02Z"},{"alias_kind":"arxiv_version","alias_value":"2107.05382v1","created_at":"2026-07-05T02:57:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.05382","created_at":"2026-07-05T02:57:02Z"},{"alias_kind":"pith_short_12","alias_value":"MUAZJ5HCYE4Z","created_at":"2026-07-05T02:57:02Z"},{"alias_kind":"pith_short_16","alias_value":"MUAZJ5HCYE4Z6RGY","created_at":"2026-07-05T02:57:02Z"},{"alias_kind":"pith_short_8","alias_value":"MUAZJ5HC","created_at":"2026-07-05T02:57:02Z"}],"graph_snapshots":[{"event_id":"sha256:0d81b1e33bebb93086e9304f4d0a4c69831fff75cf44a646c60f6573fae43506","target":"graph","created_at":"2026-07-05T02:57:02Z","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/2107.05382/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a semi-supervised learning method for building end-to-end rich transcription-style automatic speech recognition (RT-ASR) systems from small-scale rich transcription-style and large-scale common transcription-style datasets. In spontaneous speech tasks, various speech phenomena such as fillers, word fragments, laughter and coughs, etc. are often included. While common transcriptions do not give special awareness to these phenomena, rich transcriptions explicitly convert them into special phenomenon tokens as well as textual tokens. In previous studies, the textual and phenomenon toke","authors_text":"Akihiko Takashima, Mana Ihori, Naoki Makishima, Ryo Masumura, Shota Orihashi, Tomohiro Tanaka","cross_cats":["cs.LG","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-07-07T12:52:49Z","title":"End-to-End Rich Transcription-Style Automatic Speech Recognition with Semi-Supervised Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.05382","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":"sha256:536a1b66ac93f3b761adbe418245241dc6eca626b45912022c46c74abb0c4f49","target":"record","created_at":"2026-07-05T02:57:02Z","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":"20015f17bd0989ca3000392b51ab3017024c273cf103fa84aa66c3a17544c7de","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-07-07T12:52:49Z","title_canon_sha256":"6989cba20519d18db8d4b38a447f5f5def14c738f59df39d148d1bd898c9f913"},"schema_version":"1.0","source":{"id":"2107.05382","kind":"arxiv","version":1}},"canonical_sha256":"650194f4e2c1399f44d84e0e1e808f5c84c21a80846ee5e212f4af0062587680","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"650194f4e2c1399f44d84e0e1e808f5c84c21a80846ee5e212f4af0062587680","first_computed_at":"2026-07-05T02:57:02.292127Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:57:02.292127Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5/ZekyO66R+EaLThRxy+pX8Jj4rptTV0wstxGH2yrbbRn+a2nqAQnhsJmdNDjm/WKidPnQQ7dvU9hTlmTgX/Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:57:02.292552Z","signed_message":"canonical_sha256_bytes"},"source_id":"2107.05382","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:536a1b66ac93f3b761adbe418245241dc6eca626b45912022c46c74abb0c4f49","sha256:0d81b1e33bebb93086e9304f4d0a4c69831fff75cf44a646c60f6573fae43506"],"state_sha256":"4989cf0dbcde13b77ef154d817a99b0849914f8292a44bed7806f2d428952308"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ORYt2vJ7V9AFNKG1Qk+dSg+s5SMQX6wUti5LBkDv9q1pRIeNNVmP55EIFkWhujAGYAS95WzcjrwNy/2NWUHVCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T06:19:43.025557Z","bundle_sha256":"1d338aede57e79b633355f71d6f182bf18de543cb5557810ff7c84a23603da13"}}