{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:PJFVXMX5A3ASKR6RMPNFDWCP6J","short_pith_number":"pith:PJFVXMX5","canonical_record":{"source":{"id":"2502.14685","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-02-20T16:13:17Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"d01afee2773c8dc426a502182fe363d3a18dc6c9639ff56d5c721350e615a84f","abstract_canon_sha256":"17a16733c69d2d2b0a03a838ad0a6543a481a88ceeb3adf47dd175f17d0af92e"},"schema_version":"1.0"},"canonical_sha256":"7a4b5bb2fd06c12547d163da51d84ff242db0388aaf3c4e0db28ded5b3c60386","source":{"kind":"arxiv","id":"2502.14685","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.14685","created_at":"2026-07-05T10:17:31Z"},{"alias_kind":"arxiv_version","alias_value":"2502.14685v1","created_at":"2026-07-05T10:17:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.14685","created_at":"2026-07-05T10:17:31Z"},{"alias_kind":"pith_short_12","alias_value":"PJFVXMX5A3AS","created_at":"2026-07-05T10:17:31Z"},{"alias_kind":"pith_short_16","alias_value":"PJFVXMX5A3ASKR6R","created_at":"2026-07-05T10:17:31Z"},{"alias_kind":"pith_short_8","alias_value":"PJFVXMX5","created_at":"2026-07-05T10:17:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:PJFVXMX5A3ASKR6RMPNFDWCP6J","target":"record","payload":{"canonical_record":{"source":{"id":"2502.14685","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-02-20T16:13:17Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"d01afee2773c8dc426a502182fe363d3a18dc6c9639ff56d5c721350e615a84f","abstract_canon_sha256":"17a16733c69d2d2b0a03a838ad0a6543a481a88ceeb3adf47dd175f17d0af92e"},"schema_version":"1.0"},"canonical_sha256":"7a4b5bb2fd06c12547d163da51d84ff242db0388aaf3c4e0db28ded5b3c60386","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:17:31.193830Z","signature_b64":"2Mxc6vecY+To+kAaomeryUvXjXvyWPoBarJGV0HjwFJFrqlVuJ2WJEjH+8lFd95lO8qKhoPkGbe+v56sWwJtCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a4b5bb2fd06c12547d163da51d84ff242db0388aaf3c4e0db28ded5b3c60386","last_reissued_at":"2026-07-05T10:17:31.193369Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:17:31.193369Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.14685","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":"2026-07-05T10:17:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7yUFpAVX1wumjBrZC0zEz5PNMa5lFPy6fUkLCa8UvU5HqghMVjQcs0h78Bz/wNbYG/Pb4Uyv432OUNPhU7qrDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T01:55:14.580778Z"},"content_sha256":"f4148657e4f501ff8a54a7466b699853dd68701d8f9841e83fae3a834c2fa328","schema_version":"1.0","event_id":"sha256:f4148657e4f501ff8a54a7466b699853dd68701d8f9841e83fae3a834c2fa328"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:PJFVXMX5A3ASKR6RMPNFDWCP6J","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SegAug: CTC-Aligned Segmented Augmentation For Robust RNN-Transducer Based Speech Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Duc Thanh Chau, Dung Tran, Khanh Le, Tuan Vu Ho","submitted_at":"2025-02-20T16:13:17Z","abstract_excerpt":"RNN-Transducer (RNN-T) is a widely adopted architecture in speech recognition, integrating acoustic and language modeling in an end-to-end framework. However, the RNN-T predictor tends to over-rely on consecutive word dependencies in training data, leading to high deletion error rates, particularly with less common or out-of-domain phrases. Existing solutions, such as regularization and data augmentation, often compromise other aspects of performance. We propose SegAug, an alignment-based augmentation technique that generates contextually varied audio-text pairs with low sentence-level semanti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.14685","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/2502.14685/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":"2026-07-05T10:17:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pdllmYYqBGAXepxsqLmNCvs9T8iN1eix7Ye14gi6ukZsPbGOnGe+t+q9/uzf4saTf1SnNtfRptw8fLYLybxVDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T01:55:14.581312Z"},"content_sha256":"876f12f1d8f0e37d84ffd7ad16e2f41dbb2b7fb00fa45dd1643ecaa96cda8718","schema_version":"1.0","event_id":"sha256:876f12f1d8f0e37d84ffd7ad16e2f41dbb2b7fb00fa45dd1643ecaa96cda8718"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PJFVXMX5A3ASKR6RMPNFDWCP6J/bundle.json","state_url":"https://pith.science/pith/PJFVXMX5A3ASKR6RMPNFDWCP6J/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PJFVXMX5A3ASKR6RMPNFDWCP6J/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":"2026-08-07T01:55:14Z","links":{"resolver":"https://pith.science/pith/PJFVXMX5A3ASKR6RMPNFDWCP6J","bundle":"https://pith.science/pith/PJFVXMX5A3ASKR6RMPNFDWCP6J/bundle.json","state":"https://pith.science/pith/PJFVXMX5A3ASKR6RMPNFDWCP6J/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PJFVXMX5A3ASKR6RMPNFDWCP6J/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PJFVXMX5A3ASKR6RMPNFDWCP6J","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":"17a16733c69d2d2b0a03a838ad0a6543a481a88ceeb3adf47dd175f17d0af92e","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-02-20T16:13:17Z","title_canon_sha256":"d01afee2773c8dc426a502182fe363d3a18dc6c9639ff56d5c721350e615a84f"},"schema_version":"1.0","source":{"id":"2502.14685","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.14685","created_at":"2026-07-05T10:17:31Z"},{"alias_kind":"arxiv_version","alias_value":"2502.14685v1","created_at":"2026-07-05T10:17:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.14685","created_at":"2026-07-05T10:17:31Z"},{"alias_kind":"pith_short_12","alias_value":"PJFVXMX5A3AS","created_at":"2026-07-05T10:17:31Z"},{"alias_kind":"pith_short_16","alias_value":"PJFVXMX5A3ASKR6R","created_at":"2026-07-05T10:17:31Z"},{"alias_kind":"pith_short_8","alias_value":"PJFVXMX5","created_at":"2026-07-05T10:17:31Z"}],"graph_snapshots":[{"event_id":"sha256:876f12f1d8f0e37d84ffd7ad16e2f41dbb2b7fb00fa45dd1643ecaa96cda8718","target":"graph","created_at":"2026-07-05T10:17:31Z","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/2502.14685/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"RNN-Transducer (RNN-T) is a widely adopted architecture in speech recognition, integrating acoustic and language modeling in an end-to-end framework. However, the RNN-T predictor tends to over-rely on consecutive word dependencies in training data, leading to high deletion error rates, particularly with less common or out-of-domain phrases. Existing solutions, such as regularization and data augmentation, often compromise other aspects of performance. We propose SegAug, an alignment-based augmentation technique that generates contextually varied audio-text pairs with low sentence-level semanti","authors_text":"Duc Thanh Chau, Dung Tran, Khanh Le, Tuan Vu Ho","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-02-20T16:13:17Z","title":"SegAug: CTC-Aligned Segmented Augmentation For Robust RNN-Transducer Based Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.14685","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:f4148657e4f501ff8a54a7466b699853dd68701d8f9841e83fae3a834c2fa328","target":"record","created_at":"2026-07-05T10:17:31Z","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":"17a16733c69d2d2b0a03a838ad0a6543a481a88ceeb3adf47dd175f17d0af92e","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-02-20T16:13:17Z","title_canon_sha256":"d01afee2773c8dc426a502182fe363d3a18dc6c9639ff56d5c721350e615a84f"},"schema_version":"1.0","source":{"id":"2502.14685","kind":"arxiv","version":1}},"canonical_sha256":"7a4b5bb2fd06c12547d163da51d84ff242db0388aaf3c4e0db28ded5b3c60386","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7a4b5bb2fd06c12547d163da51d84ff242db0388aaf3c4e0db28ded5b3c60386","first_computed_at":"2026-07-05T10:17:31.193369Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:17:31.193369Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2Mxc6vecY+To+kAaomeryUvXjXvyWPoBarJGV0HjwFJFrqlVuJ2WJEjH+8lFd95lO8qKhoPkGbe+v56sWwJtCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:17:31.193830Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.14685","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f4148657e4f501ff8a54a7466b699853dd68701d8f9841e83fae3a834c2fa328","sha256:876f12f1d8f0e37d84ffd7ad16e2f41dbb2b7fb00fa45dd1643ecaa96cda8718"],"state_sha256":"2c3d77be980bf9176682bd9c25d36b1c1fa53611a48d55a58dc2055ceb0ec87f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8sCjO2DJhlIRBwwymvpTEo1qvHML3vQOUdtIlcbsXsYbjVXi6o9T8x9QYwF1om4ivXEb48P0OGTfwiS/F5UqCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T01:55:14.586453Z","bundle_sha256":"f959c34f3c8be3216e937c2288c422887ed67fed78aaab42ddd4da7062c35496"}}