{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:752JZ6O4AFM3KQXIBOGSYNKFME","short_pith_number":"pith:752JZ6O4","canonical_record":{"source":{"id":"2406.10052","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-06-14T14:07:26Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"68b51d3c74b0d905ba9e40355ac3b2e9a39b93b4ad75d5495671e150552d57e0","abstract_canon_sha256":"b13c15399b0f462bc2a1558ee448a494e613f83c51f74ef82b016c1e8e7ac591"},"schema_version":"1.0"},"canonical_sha256":"ff749cf9dc0159b542e80b8d2c35456126358ef7b8a4e8940ddeba6b08acfbd4","source":{"kind":"arxiv","id":"2406.10052","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.10052","created_at":"2026-07-05T10:57:52Z"},{"alias_kind":"arxiv_version","alias_value":"2406.10052v1","created_at":"2026-07-05T10:57:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10052","created_at":"2026-07-05T10:57:52Z"},{"alias_kind":"pith_short_12","alias_value":"752JZ6O4AFM3","created_at":"2026-07-05T10:57:52Z"},{"alias_kind":"pith_short_16","alias_value":"752JZ6O4AFM3KQXI","created_at":"2026-07-05T10:57:52Z"},{"alias_kind":"pith_short_8","alias_value":"752JZ6O4","created_at":"2026-07-05T10:57:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:752JZ6O4AFM3KQXIBOGSYNKFME","target":"record","payload":{"canonical_record":{"source":{"id":"2406.10052","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-06-14T14:07:26Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"68b51d3c74b0d905ba9e40355ac3b2e9a39b93b4ad75d5495671e150552d57e0","abstract_canon_sha256":"b13c15399b0f462bc2a1558ee448a494e613f83c51f74ef82b016c1e8e7ac591"},"schema_version":"1.0"},"canonical_sha256":"ff749cf9dc0159b542e80b8d2c35456126358ef7b8a4e8940ddeba6b08acfbd4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:57:52.990504Z","signature_b64":"4NKgeUFdjoUnVWpIBQ2ZEKnelQIytYw8j0YPnAn5GtpGH4QfzMVXaIRM3UM4ysOw7tY2AtAW1Z0C821DHv1yAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff749cf9dc0159b542e80b8d2c35456126358ef7b8a4e8940ddeba6b08acfbd4","last_reissued_at":"2026-07-05T10:57:52.990010Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:57:52.990010Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.10052","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":"2026-07-05T10:57:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YE0NZxBxwxZPw2cyxJNJp8VF7qmHDouMxSBiOtM/BgC7k659zgpQhsOU1FuH6J1t+12aIMltN68gyxgj7d8/CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T23:11:46.479548Z"},"content_sha256":"9c713df577736603ed3fb20e103d5da381ad9692d1751de3a3067c5dd9e75a3c","schema_version":"1.0","event_id":"sha256:9c713df577736603ed3fb20e103d5da381ad9692d1751de3a3067c5dd9e75a3c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:752JZ6O4AFM3KQXIBOGSYNKFME","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Simul-Whisper: Attention-Guided Streaming Whisper with Truncation Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Guodong Lin, Guoqiang Hu, Haoyu Wang, Jian Li, Wei-Qiang Zhang","submitted_at":"2024-06-14T14:07:26Z","abstract_excerpt":"As a robust and large-scale multilingual speech recognition model, Whisper has demonstrated impressive results in many low-resource and out-of-distribution scenarios. However, its encoder-decoder structure hinders its application to streaming speech recognition. In this paper, we introduce Simul-Whisper, which uses the time alignment embedded in Whisper's cross-attention to guide auto-regressive decoding and achieve chunk-based streaming ASR without any fine-tuning of the pre-trained model. Furthermore, we observe the negative effect of the truncated words at the chunk boundaries on the decodi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10052","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/2406.10052/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":"2026-07-05T10:57:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n4sIvrdvY+dLksMuc4QsFcQhX+Ca8RuRQznSYl8Jl57w48ele5K4i3OozsObbWLAnXj6hK9/p9q9WGcIY241Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T23:11:46.480072Z"},"content_sha256":"adcff8fe2f562ec3752e777b38443a496d6899c5b72865e2286bcbfa121c1c5d","schema_version":"1.0","event_id":"sha256:adcff8fe2f562ec3752e777b38443a496d6899c5b72865e2286bcbfa121c1c5d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/752JZ6O4AFM3KQXIBOGSYNKFME/bundle.json","state_url":"https://pith.science/pith/752JZ6O4AFM3KQXIBOGSYNKFME/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/752JZ6O4AFM3KQXIBOGSYNKFME/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":"2026-08-07T23:11:46Z","links":{"resolver":"https://pith.science/pith/752JZ6O4AFM3KQXIBOGSYNKFME","bundle":"https://pith.science/pith/752JZ6O4AFM3KQXIBOGSYNKFME/bundle.json","state":"https://pith.science/pith/752JZ6O4AFM3KQXIBOGSYNKFME/state.json","well_known_bundle":"https://pith.science/.well-known/pith/752JZ6O4AFM3KQXIBOGSYNKFME/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:752JZ6O4AFM3KQXIBOGSYNKFME","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":"b13c15399b0f462bc2a1558ee448a494e613f83c51f74ef82b016c1e8e7ac591","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-06-14T14:07:26Z","title_canon_sha256":"68b51d3c74b0d905ba9e40355ac3b2e9a39b93b4ad75d5495671e150552d57e0"},"schema_version":"1.0","source":{"id":"2406.10052","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.10052","created_at":"2026-07-05T10:57:52Z"},{"alias_kind":"arxiv_version","alias_value":"2406.10052v1","created_at":"2026-07-05T10:57:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10052","created_at":"2026-07-05T10:57:52Z"},{"alias_kind":"pith_short_12","alias_value":"752JZ6O4AFM3","created_at":"2026-07-05T10:57:52Z"},{"alias_kind":"pith_short_16","alias_value":"752JZ6O4AFM3KQXI","created_at":"2026-07-05T10:57:52Z"},{"alias_kind":"pith_short_8","alias_value":"752JZ6O4","created_at":"2026-07-05T10:57:52Z"}],"graph_snapshots":[{"event_id":"sha256:adcff8fe2f562ec3752e777b38443a496d6899c5b72865e2286bcbfa121c1c5d","target":"graph","created_at":"2026-07-05T10:57:52Z","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/2406.10052/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As a robust and large-scale multilingual speech recognition model, Whisper has demonstrated impressive results in many low-resource and out-of-distribution scenarios. However, its encoder-decoder structure hinders its application to streaming speech recognition. In this paper, we introduce Simul-Whisper, which uses the time alignment embedded in Whisper's cross-attention to guide auto-regressive decoding and achieve chunk-based streaming ASR without any fine-tuning of the pre-trained model. Furthermore, we observe the negative effect of the truncated words at the chunk boundaries on the decodi","authors_text":"Guodong Lin, Guoqiang Hu, Haoyu Wang, Jian Li, Wei-Qiang Zhang","cross_cats":["cs.CL","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-06-14T14:07:26Z","title":"Simul-Whisper: Attention-Guided Streaming Whisper with Truncation Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10052","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":"sha256:9c713df577736603ed3fb20e103d5da381ad9692d1751de3a3067c5dd9e75a3c","target":"record","created_at":"2026-07-05T10:57:52Z","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":"b13c15399b0f462bc2a1558ee448a494e613f83c51f74ef82b016c1e8e7ac591","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-06-14T14:07:26Z","title_canon_sha256":"68b51d3c74b0d905ba9e40355ac3b2e9a39b93b4ad75d5495671e150552d57e0"},"schema_version":"1.0","source":{"id":"2406.10052","kind":"arxiv","version":1}},"canonical_sha256":"ff749cf9dc0159b542e80b8d2c35456126358ef7b8a4e8940ddeba6b08acfbd4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ff749cf9dc0159b542e80b8d2c35456126358ef7b8a4e8940ddeba6b08acfbd4","first_computed_at":"2026-07-05T10:57:52.990010Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:57:52.990010Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4NKgeUFdjoUnVWpIBQ2ZEKnelQIytYw8j0YPnAn5GtpGH4QfzMVXaIRM3UM4ysOw7tY2AtAW1Z0C821DHv1yAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:57:52.990504Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.10052","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9c713df577736603ed3fb20e103d5da381ad9692d1751de3a3067c5dd9e75a3c","sha256:adcff8fe2f562ec3752e777b38443a496d6899c5b72865e2286bcbfa121c1c5d"],"state_sha256":"51cdefb1bf3a3c153b11c238fe93e09e0c9eaafa5e81bc877874f2b500b32a67"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jKA2NdTQ32XRj7UJIbt041OofscedxShfPnE0WZOgCoIwAZTzNwu5U1UEwjA9chTQSiNpgp41RX7/PbCtPlcDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T23:11:46.483787Z","bundle_sha256":"0ef0322cb81f7b91abcdfe3ede78e1180a09aabe2d7c403c3673d8ea0ecaaabf"}}