{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:6KRVKZJWOMSBJ55YJA753ZFFUB","short_pith_number":"pith:6KRVKZJW","canonical_record":{"source":{"id":"2307.12767","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-07-24T13:12:50Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"ec1a0da9d4b85edc29975886d6dc9d6349f0f417b50574422e7dcdb939d53d16","abstract_canon_sha256":"ccc4e509e58f83ca9265e82fe73d0887991121bfb0790e07b6dc7cebd5eb1203"},"schema_version":"1.0"},"canonical_sha256":"f2a3556536732414f7b8483fdde4a5a04034ea3ea721373a73385561bf030d0b","source":{"kind":"arxiv","id":"2307.12767","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.12767","created_at":"2026-07-05T06:33:58Z"},{"alias_kind":"arxiv_version","alias_value":"2307.12767v1","created_at":"2026-07-05T06:33:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.12767","created_at":"2026-07-05T06:33:58Z"},{"alias_kind":"pith_short_12","alias_value":"6KRVKZJWOMSB","created_at":"2026-07-05T06:33:58Z"},{"alias_kind":"pith_short_16","alias_value":"6KRVKZJWOMSBJ55Y","created_at":"2026-07-05T06:33:58Z"},{"alias_kind":"pith_short_8","alias_value":"6KRVKZJW","created_at":"2026-07-05T06:33:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:6KRVKZJWOMSBJ55YJA753ZFFUB","target":"record","payload":{"canonical_record":{"source":{"id":"2307.12767","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-07-24T13:12:50Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"ec1a0da9d4b85edc29975886d6dc9d6349f0f417b50574422e7dcdb939d53d16","abstract_canon_sha256":"ccc4e509e58f83ca9265e82fe73d0887991121bfb0790e07b6dc7cebd5eb1203"},"schema_version":"1.0"},"canonical_sha256":"f2a3556536732414f7b8483fdde4a5a04034ea3ea721373a73385561bf030d0b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:33:58.359169Z","signature_b64":"jVNyA6qEkQ48GkpxY6TxKsRcaS6l/QlYd9Gy6i1mRf/SKSWlnim3/o54wB05cv31DAk2iy6Fd/Ejz/763OX7CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f2a3556536732414f7b8483fdde4a5a04034ea3ea721373a73385561bf030d0b","last_reissued_at":"2026-07-05T06:33:58.358732Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:33:58.358732Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.12767","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":"2026-07-05T06:33:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OqkjR8jPON+7pxf18eLRhPD15LwWWSOgXJiyUs+tpqSE+O0s8dIKyE+OiAXq8GFCo7Z8aiwLv2Pu6uoY6WFgAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T19:53:01.541554Z"},"content_sha256":"72a4f48d09a005d7be71ddd827d3d458285f7122273edb3417e4c8aaefccd756","schema_version":"1.0","event_id":"sha256:72a4f48d09a005d7be71ddd827d3d458285f7122273edb3417e4c8aaefccd756"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:6KRVKZJWOMSBJ55YJA753ZFFUB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Integration of Frame- and Label-synchronous Beam Search for Streaming Encoder-decoder Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Emiru Tsunoo, Hayato Futami, Shinji Watanabe, Siddhant Arora, Yosuke Kashiwagi","submitted_at":"2023-07-24T13:12:50Z","abstract_excerpt":"Although frame-based models, such as CTC and transducers, have an affinity for streaming automatic speech recognition, their decoding uses no future knowledge, which could lead to incorrect pruning. Conversely, label-based attention encoder-decoder mitigates this issue using soft attention to the input, while it tends to overestimate labels biased towards its training domain, unlike CTC. We exploit these complementary attributes and propose to integrate the frame- and label-synchronous (F-/L-Sync) decoding alternately performed within a single beam-search scheme. F-Sync decoding leads the deco"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.12767","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/2307.12767/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":"2026-07-05T06:33:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3nTc+7B0hGUsm7+nHf6LYqxOI4hfvjugVTd/FOFUvKzfsYfiGywngEvCl67k+L9E+Ljq3IvfNyKPYB0gCdkBDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T19:53:01.542510Z"},"content_sha256":"a4f61af3f9b752ca9baecd645ce643d1b862ebbd7379ea1a0d99b0745b2932d6","schema_version":"1.0","event_id":"sha256:a4f61af3f9b752ca9baecd645ce643d1b862ebbd7379ea1a0d99b0745b2932d6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6KRVKZJWOMSBJ55YJA753ZFFUB/bundle.json","state_url":"https://pith.science/pith/6KRVKZJWOMSBJ55YJA753ZFFUB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6KRVKZJWOMSBJ55YJA753ZFFUB/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":"2026-08-21T19:53:01Z","links":{"resolver":"https://pith.science/pith/6KRVKZJWOMSBJ55YJA753ZFFUB","bundle":"https://pith.science/pith/6KRVKZJWOMSBJ55YJA753ZFFUB/bundle.json","state":"https://pith.science/pith/6KRVKZJWOMSBJ55YJA753ZFFUB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6KRVKZJWOMSBJ55YJA753ZFFUB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:6KRVKZJWOMSBJ55YJA753ZFFUB","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":"ccc4e509e58f83ca9265e82fe73d0887991121bfb0790e07b6dc7cebd5eb1203","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-07-24T13:12:50Z","title_canon_sha256":"ec1a0da9d4b85edc29975886d6dc9d6349f0f417b50574422e7dcdb939d53d16"},"schema_version":"1.0","source":{"id":"2307.12767","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.12767","created_at":"2026-07-05T06:33:58Z"},{"alias_kind":"arxiv_version","alias_value":"2307.12767v1","created_at":"2026-07-05T06:33:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.12767","created_at":"2026-07-05T06:33:58Z"},{"alias_kind":"pith_short_12","alias_value":"6KRVKZJWOMSB","created_at":"2026-07-05T06:33:58Z"},{"alias_kind":"pith_short_16","alias_value":"6KRVKZJWOMSBJ55Y","created_at":"2026-07-05T06:33:58Z"},{"alias_kind":"pith_short_8","alias_value":"6KRVKZJW","created_at":"2026-07-05T06:33:58Z"}],"graph_snapshots":[{"event_id":"sha256:a4f61af3f9b752ca9baecd645ce643d1b862ebbd7379ea1a0d99b0745b2932d6","target":"graph","created_at":"2026-07-05T06:33:58Z","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/2307.12767/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Although frame-based models, such as CTC and transducers, have an affinity for streaming automatic speech recognition, their decoding uses no future knowledge, which could lead to incorrect pruning. Conversely, label-based attention encoder-decoder mitigates this issue using soft attention to the input, while it tends to overestimate labels biased towards its training domain, unlike CTC. We exploit these complementary attributes and propose to integrate the frame- and label-synchronous (F-/L-Sync) decoding alternately performed within a single beam-search scheme. F-Sync decoding leads the deco","authors_text":"Emiru Tsunoo, Hayato Futami, Shinji Watanabe, Siddhant Arora, Yosuke Kashiwagi","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-07-24T13:12:50Z","title":"Integration of Frame- and Label-synchronous Beam Search for Streaming Encoder-decoder Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.12767","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":"sha256:72a4f48d09a005d7be71ddd827d3d458285f7122273edb3417e4c8aaefccd756","target":"record","created_at":"2026-07-05T06:33:58Z","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":"ccc4e509e58f83ca9265e82fe73d0887991121bfb0790e07b6dc7cebd5eb1203","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-07-24T13:12:50Z","title_canon_sha256":"ec1a0da9d4b85edc29975886d6dc9d6349f0f417b50574422e7dcdb939d53d16"},"schema_version":"1.0","source":{"id":"2307.12767","kind":"arxiv","version":1}},"canonical_sha256":"f2a3556536732414f7b8483fdde4a5a04034ea3ea721373a73385561bf030d0b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f2a3556536732414f7b8483fdde4a5a04034ea3ea721373a73385561bf030d0b","first_computed_at":"2026-07-05T06:33:58.358732Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:33:58.358732Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jVNyA6qEkQ48GkpxY6TxKsRcaS6l/QlYd9Gy6i1mRf/SKSWlnim3/o54wB05cv31DAk2iy6Fd/Ejz/763OX7CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:33:58.359169Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.12767","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:72a4f48d09a005d7be71ddd827d3d458285f7122273edb3417e4c8aaefccd756","sha256:a4f61af3f9b752ca9baecd645ce643d1b862ebbd7379ea1a0d99b0745b2932d6"],"state_sha256":"29bcf1d45be81d3e469a00a132c89723aad7bee23c4902d4fbbd9f3089cea500"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zpXpnbKXipMER0vNXyWhAe8YOdjxx6MsgjAGvZLOE/2ggv98uCfc4gRanVMNioX5GQYTNTSm0CDA+87BO5tgDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T19:53:01.550278Z","bundle_sha256":"b5bd0cf82ed24e03979675a477fd7441df1f1d07eda027528d5f5406bd61a1de"}}