{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:GGSV7WW77P4XHOHIYFF5KZVFKH","short_pith_number":"pith:GGSV7WW7","canonical_record":{"source":{"id":"2210.15876","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-10-28T03:54:57Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"dfbc981f1c7ad658e82c3bb713ab0d1f04366591bd2a6deaa8bdb3557cbd6268","abstract_canon_sha256":"6c19f20b4c026c7df5415af6f13a204435e1740584e9d6a3171b9c5619967ebb"},"schema_version":"1.0"},"canonical_sha256":"31a55fdadffbf973b8e8c14bd566a551d3f67afa95c775d066f6ffecb5e6486f","source":{"kind":"arxiv","id":"2210.15876","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.15876","created_at":"2026-07-05T06:13:37Z"},{"alias_kind":"arxiv_version","alias_value":"2210.15876v2","created_at":"2026-07-05T06:13:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.15876","created_at":"2026-07-05T06:13:37Z"},{"alias_kind":"pith_short_12","alias_value":"GGSV7WW77P4X","created_at":"2026-07-05T06:13:37Z"},{"alias_kind":"pith_short_16","alias_value":"GGSV7WW77P4XHOHI","created_at":"2026-07-05T06:13:37Z"},{"alias_kind":"pith_short_8","alias_value":"GGSV7WW7","created_at":"2026-07-05T06:13:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:GGSV7WW77P4XHOHIYFF5KZVFKH","target":"record","payload":{"canonical_record":{"source":{"id":"2210.15876","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-10-28T03:54:57Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"dfbc981f1c7ad658e82c3bb713ab0d1f04366591bd2a6deaa8bdb3557cbd6268","abstract_canon_sha256":"6c19f20b4c026c7df5415af6f13a204435e1740584e9d6a3171b9c5619967ebb"},"schema_version":"1.0"},"canonical_sha256":"31a55fdadffbf973b8e8c14bd566a551d3f67afa95c775d066f6ffecb5e6486f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:13:37.264748Z","signature_b64":"ORkz5IbUoJ/ey04ShJ04aRZHbN5vuWlx9d/P3A9HJ5r+XSCbSvrbyMYfk9ieWJHVWuyYifc/ENAHtTay4hP5DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31a55fdadffbf973b8e8c14bd566a551d3f67afa95c775d066f6ffecb5e6486f","last_reissued_at":"2026-07-05T06:13:37.264251Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:13:37.264251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.15876","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":"2026-07-05T06:13:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LMdd031k07SbNo4ElwSuJi9wFpE5s8bpDkqaeOXfuKAz440xjlnU5nsIsrQAe11fnz31poF/IeSS8pRBYBoUCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T09:26:02.876101Z"},"content_sha256":"f12ff9a5db4609d2eb7636a468309773b1d9d0da45a75de93bf9ecb4e039cbcd","schema_version":"1.0","event_id":"sha256:f12ff9a5db4609d2eb7636a468309773b1d9d0da45a75de93bf9ecb4e039cbcd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:GGSV7WW77P4XHOHIYFF5KZVFKH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Random Utterance Concatenation Based Data Augmentation for Improving Short-video Speech Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Haihua Xu, Lu Lu, Tao Han, Tze Yuang Chong, Van Tung Pham, Yerbolat Khassanov, Yi He, Yist Y. Lin, Zejun Ma","submitted_at":"2022-10-28T03:54:57Z","abstract_excerpt":"One of limitations in end-to-end automatic speech recognition (ASR) framework is its performance would be compromised if train-test utterance lengths are mismatched. In this paper, we propose an on-the-fly random utterance concatenation (RUC) based data augmentation method to alleviate train-test utterance length mismatch issue for short-video ASR task. Specifically, we are motivated by observations that our human-transcribed training utterances tend to be much shorter for short-video spontaneous speech (~3 seconds on average), while our test utterance generated from voice activity detection f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.15876","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/2210.15876/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":"2026-07-05T06:13:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cgOuK/BYoAd0JRB58supkt6dVUEO2umkzKd3mvw1XxNS7FsPnp1+IinxQIQhKpEnmmG3ga2lD9cEzwC8+QDfDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T09:26:02.876895Z"},"content_sha256":"8be3d0011d3a10dd886a367321623941c3cc2b8ce90f2f9b9d244bfd7bb857e4","schema_version":"1.0","event_id":"sha256:8be3d0011d3a10dd886a367321623941c3cc2b8ce90f2f9b9d244bfd7bb857e4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GGSV7WW77P4XHOHIYFF5KZVFKH/bundle.json","state_url":"https://pith.science/pith/GGSV7WW77P4XHOHIYFF5KZVFKH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GGSV7WW77P4XHOHIYFF5KZVFKH/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":"2026-08-14T09:26:02Z","links":{"resolver":"https://pith.science/pith/GGSV7WW77P4XHOHIYFF5KZVFKH","bundle":"https://pith.science/pith/GGSV7WW77P4XHOHIYFF5KZVFKH/bundle.json","state":"https://pith.science/pith/GGSV7WW77P4XHOHIYFF5KZVFKH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GGSV7WW77P4XHOHIYFF5KZVFKH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:GGSV7WW77P4XHOHIYFF5KZVFKH","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":"6c19f20b4c026c7df5415af6f13a204435e1740584e9d6a3171b9c5619967ebb","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-10-28T03:54:57Z","title_canon_sha256":"dfbc981f1c7ad658e82c3bb713ab0d1f04366591bd2a6deaa8bdb3557cbd6268"},"schema_version":"1.0","source":{"id":"2210.15876","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.15876","created_at":"2026-07-05T06:13:37Z"},{"alias_kind":"arxiv_version","alias_value":"2210.15876v2","created_at":"2026-07-05T06:13:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.15876","created_at":"2026-07-05T06:13:37Z"},{"alias_kind":"pith_short_12","alias_value":"GGSV7WW77P4X","created_at":"2026-07-05T06:13:37Z"},{"alias_kind":"pith_short_16","alias_value":"GGSV7WW77P4XHOHI","created_at":"2026-07-05T06:13:37Z"},{"alias_kind":"pith_short_8","alias_value":"GGSV7WW7","created_at":"2026-07-05T06:13:37Z"}],"graph_snapshots":[{"event_id":"sha256:8be3d0011d3a10dd886a367321623941c3cc2b8ce90f2f9b9d244bfd7bb857e4","target":"graph","created_at":"2026-07-05T06:13:37Z","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/2210.15876/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"One of limitations in end-to-end automatic speech recognition (ASR) framework is its performance would be compromised if train-test utterance lengths are mismatched. In this paper, we propose an on-the-fly random utterance concatenation (RUC) based data augmentation method to alleviate train-test utterance length mismatch issue for short-video ASR task. Specifically, we are motivated by observations that our human-transcribed training utterances tend to be much shorter for short-video spontaneous speech (~3 seconds on average), while our test utterance generated from voice activity detection f","authors_text":"Haihua Xu, Lu Lu, Tao Han, Tze Yuang Chong, Van Tung Pham, Yerbolat Khassanov, Yi He, Yist Y. Lin, Zejun Ma","cross_cats":["cs.CL","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-10-28T03:54:57Z","title":"Random Utterance Concatenation Based Data Augmentation for Improving Short-video Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.15876","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:f12ff9a5db4609d2eb7636a468309773b1d9d0da45a75de93bf9ecb4e039cbcd","target":"record","created_at":"2026-07-05T06:13:37Z","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":"6c19f20b4c026c7df5415af6f13a204435e1740584e9d6a3171b9c5619967ebb","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-10-28T03:54:57Z","title_canon_sha256":"dfbc981f1c7ad658e82c3bb713ab0d1f04366591bd2a6deaa8bdb3557cbd6268"},"schema_version":"1.0","source":{"id":"2210.15876","kind":"arxiv","version":2}},"canonical_sha256":"31a55fdadffbf973b8e8c14bd566a551d3f67afa95c775d066f6ffecb5e6486f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"31a55fdadffbf973b8e8c14bd566a551d3f67afa95c775d066f6ffecb5e6486f","first_computed_at":"2026-07-05T06:13:37.264251Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:13:37.264251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ORkz5IbUoJ/ey04ShJ04aRZHbN5vuWlx9d/P3A9HJ5r+XSCbSvrbyMYfk9ieWJHVWuyYifc/ENAHtTay4hP5DA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:13:37.264748Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.15876","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f12ff9a5db4609d2eb7636a468309773b1d9d0da45a75de93bf9ecb4e039cbcd","sha256:8be3d0011d3a10dd886a367321623941c3cc2b8ce90f2f9b9d244bfd7bb857e4"],"state_sha256":"7b7b5e38c47512970ec66009d1341c54e76f80a2440f1315891d0b34a23d8142"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5zON25Y15t9ZyCiV4jyf3D2yIYfF5CXTUZKSjL9WzwlFvYP+pLucoDuVOqrqhPetxttCxhYBocEAS55+q29DAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T09:26:02.881885Z","bundle_sha256":"b7e42ca2d9879b32264ae813907f0b64f962182c9d27248d072ccba28d02fb54"}}