{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:7HDUMZ3JHVWLHRHVFD563IBM6Z","short_pith_number":"pith:7HDUMZ3J","canonical_record":{"source":{"id":"2506.12154","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-13T18:19:09Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"6e4e8bb1d837984e5bf0c7eecc83c80990625c27563cd3c86d910e33dbc88be4","abstract_canon_sha256":"f7adc7736b3d232fa31dd5f4e459c2e1b6cd9f46acdf8f19129428a4abead5c7"},"schema_version":"1.0"},"canonical_sha256":"f9c74667693d6cb3c4f528fbeda02cf67c2706da5a2001717e2b9355add9afaa","source":{"kind":"arxiv","id":"2506.12154","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.12154","created_at":"2026-07-05T11:21:22Z"},{"alias_kind":"arxiv_version","alias_value":"2506.12154v1","created_at":"2026-07-05T11:21:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.12154","created_at":"2026-07-05T11:21:22Z"},{"alias_kind":"pith_short_12","alias_value":"7HDUMZ3JHVWL","created_at":"2026-07-05T11:21:22Z"},{"alias_kind":"pith_short_16","alias_value":"7HDUMZ3JHVWLHRHV","created_at":"2026-07-05T11:21:22Z"},{"alias_kind":"pith_short_8","alias_value":"7HDUMZ3J","created_at":"2026-07-05T11:21:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:7HDUMZ3JHVWLHRHVFD563IBM6Z","target":"record","payload":{"canonical_record":{"source":{"id":"2506.12154","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-13T18:19:09Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"6e4e8bb1d837984e5bf0c7eecc83c80990625c27563cd3c86d910e33dbc88be4","abstract_canon_sha256":"f7adc7736b3d232fa31dd5f4e459c2e1b6cd9f46acdf8f19129428a4abead5c7"},"schema_version":"1.0"},"canonical_sha256":"f9c74667693d6cb3c4f528fbeda02cf67c2706da5a2001717e2b9355add9afaa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:22.180404Z","signature_b64":"TIDMug2NtNqoxi7OuJbU7jbbXRB+r95nsth9uLxgUdtApPpMuoXL0CksJQXr7ymjuGQ1nOBvHz/vQUADCW7FBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9c74667693d6cb3c4f528fbeda02cf67c2706da5a2001717e2b9355add9afaa","last_reissued_at":"2026-07-05T11:21:22.179933Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:22.179933Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.12154","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":"2026-07-05T11:21:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yeouPZ2GN6UFp8cWcPVFmknvnFUwtCUUyZTGkhJ4IRUHNMTKUJWmnlcY7P63y2hHny+eXsd+TDFx/EXr14RaAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T04:14:31.536892Z"},"content_sha256":"5e6978bb4d0b298e71401df505d008745eb4529949a16e4ff411fba3cf47de0e","schema_version":"1.0","event_id":"sha256:5e6978bb4d0b298e71401df505d008745eb4529949a16e4ff411fba3cf47de0e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:7HDUMZ3JHVWLHRHVFD563IBM6Z","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adapting Whisper for Streaming Speech Recognition via Two-Pass Decoding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Anshul Wadhawan, Apurv Verma, Binbin Zhang, Brendan Fahy, Denglin Jiang, Haoran Zhou, Michele M. Franceschini, Qiaochu Song, Srivas Prasad, Vinay Ramesh, Xingchen Song, Zhendong Peng","submitted_at":"2025-06-13T18:19:09Z","abstract_excerpt":"OpenAI Whisper is a family of robust Automatic Speech Recognition (ASR) models trained on 680,000 hours of audio. However, its encoder-decoder architecture, trained with a sequence-to-sequence objective, lacks native support for streaming ASR. In this paper, we fine-tune Whisper for streaming ASR using the WeNet toolkit by adopting a Unified Two-pass (U2) structure. We introduce an additional Connectionist Temporal Classification (CTC) decoder trained with causal attention masks to generate streaming partial transcripts, while the original Whisper decoder reranks these partial outputs. Our exp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.12154","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/2506.12154/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":"2026-07-05T11:21:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jp0fdocTyx2lNc05dNxaHLGe4jVWHXGeABLPLlAF7f9Tg2htCmLQLvoS+2UQsOZQ8DrwSnwFQHranrvuZErHDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T04:14:31.537412Z"},"content_sha256":"724ce22cdec48b16a3302ea6bc8ecb4c5b6ddfba22adaf00612053f699bf8d71","schema_version":"1.0","event_id":"sha256:724ce22cdec48b16a3302ea6bc8ecb4c5b6ddfba22adaf00612053f699bf8d71"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7HDUMZ3JHVWLHRHVFD563IBM6Z/bundle.json","state_url":"https://pith.science/pith/7HDUMZ3JHVWLHRHVFD563IBM6Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7HDUMZ3JHVWLHRHVFD563IBM6Z/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":"2026-08-06T04:14:31Z","links":{"resolver":"https://pith.science/pith/7HDUMZ3JHVWLHRHVFD563IBM6Z","bundle":"https://pith.science/pith/7HDUMZ3JHVWLHRHVFD563IBM6Z/bundle.json","state":"https://pith.science/pith/7HDUMZ3JHVWLHRHVFD563IBM6Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7HDUMZ3JHVWLHRHVFD563IBM6Z/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7HDUMZ3JHVWLHRHVFD563IBM6Z","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":"f7adc7736b3d232fa31dd5f4e459c2e1b6cd9f46acdf8f19129428a4abead5c7","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-13T18:19:09Z","title_canon_sha256":"6e4e8bb1d837984e5bf0c7eecc83c80990625c27563cd3c86d910e33dbc88be4"},"schema_version":"1.0","source":{"id":"2506.12154","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.12154","created_at":"2026-07-05T11:21:22Z"},{"alias_kind":"arxiv_version","alias_value":"2506.12154v1","created_at":"2026-07-05T11:21:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.12154","created_at":"2026-07-05T11:21:22Z"},{"alias_kind":"pith_short_12","alias_value":"7HDUMZ3JHVWL","created_at":"2026-07-05T11:21:22Z"},{"alias_kind":"pith_short_16","alias_value":"7HDUMZ3JHVWLHRHV","created_at":"2026-07-05T11:21:22Z"},{"alias_kind":"pith_short_8","alias_value":"7HDUMZ3J","created_at":"2026-07-05T11:21:22Z"}],"graph_snapshots":[{"event_id":"sha256:724ce22cdec48b16a3302ea6bc8ecb4c5b6ddfba22adaf00612053f699bf8d71","target":"graph","created_at":"2026-07-05T11:21:22Z","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/2506.12154/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"OpenAI Whisper is a family of robust Automatic Speech Recognition (ASR) models trained on 680,000 hours of audio. However, its encoder-decoder architecture, trained with a sequence-to-sequence objective, lacks native support for streaming ASR. In this paper, we fine-tune Whisper for streaming ASR using the WeNet toolkit by adopting a Unified Two-pass (U2) structure. We introduce an additional Connectionist Temporal Classification (CTC) decoder trained with causal attention masks to generate streaming partial transcripts, while the original Whisper decoder reranks these partial outputs. Our exp","authors_text":"Anshul Wadhawan, Apurv Verma, Binbin Zhang, Brendan Fahy, Denglin Jiang, Haoran Zhou, Michele M. Franceschini, Qiaochu Song, Srivas Prasad, Vinay Ramesh, Xingchen Song, Zhendong Peng","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-13T18:19:09Z","title":"Adapting Whisper for Streaming Speech Recognition via Two-Pass Decoding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.12154","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":"sha256:5e6978bb4d0b298e71401df505d008745eb4529949a16e4ff411fba3cf47de0e","target":"record","created_at":"2026-07-05T11:21:22Z","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":"f7adc7736b3d232fa31dd5f4e459c2e1b6cd9f46acdf8f19129428a4abead5c7","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-13T18:19:09Z","title_canon_sha256":"6e4e8bb1d837984e5bf0c7eecc83c80990625c27563cd3c86d910e33dbc88be4"},"schema_version":"1.0","source":{"id":"2506.12154","kind":"arxiv","version":1}},"canonical_sha256":"f9c74667693d6cb3c4f528fbeda02cf67c2706da5a2001717e2b9355add9afaa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f9c74667693d6cb3c4f528fbeda02cf67c2706da5a2001717e2b9355add9afaa","first_computed_at":"2026-07-05T11:21:22.179933Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:21:22.179933Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TIDMug2NtNqoxi7OuJbU7jbbXRB+r95nsth9uLxgUdtApPpMuoXL0CksJQXr7ymjuGQ1nOBvHz/vQUADCW7FBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:21:22.180404Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.12154","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5e6978bb4d0b298e71401df505d008745eb4529949a16e4ff411fba3cf47de0e","sha256:724ce22cdec48b16a3302ea6bc8ecb4c5b6ddfba22adaf00612053f699bf8d71"],"state_sha256":"fff38f0ff43d116ef8c6f2336510c55718fadafb5b11b1162c3b1995eb92785e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hHnBdmnJFCCytW/2ir/ntxAijfPZx2cEjW6B07IHM+TWHmefa/o6fZypIDDpNN7IpNpshghOR+cOLMkI/TiRCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T04:14:31.542491Z","bundle_sha256":"524f639ae9d0aea0e90141ba86744c12fbeb9c3dde0c337c3545ea603cfde6cf"}}