{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:RSP46HPTHPD5JBXNBVW2IJ56ZO","short_pith_number":"pith:RSP46HPT","canonical_record":{"source":{"id":"2406.09950","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-06-14T11:53:14Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"cb615d5bf8e45cfc529cc53b62ca82b45aa182c05feb85625f815b5d4e041d93","abstract_canon_sha256":"aa8b3918ded87f10e0f810c18d3822d066efb61bba87fc041410710bb15ac48d"},"schema_version":"1.0"},"canonical_sha256":"8c9fcf1df33bc7d486ed0d6da427becbbd8b9c0473b0743c4ab3df8d2baeb7e3","source":{"kind":"arxiv","id":"2406.09950","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.09950","created_at":"2026-07-05T08:32:02Z"},{"alias_kind":"arxiv_version","alias_value":"2406.09950v1","created_at":"2026-07-05T08:32:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09950","created_at":"2026-07-05T08:32:02Z"},{"alias_kind":"pith_short_12","alias_value":"RSP46HPTHPD5","created_at":"2026-07-05T08:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"RSP46HPTHPD5JBXN","created_at":"2026-07-05T08:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"RSP46HPT","created_at":"2026-07-05T08:32:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:RSP46HPTHPD5JBXNBVW2IJ56ZO","target":"record","payload":{"canonical_record":{"source":{"id":"2406.09950","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-06-14T11:53:14Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"cb615d5bf8e45cfc529cc53b62ca82b45aa182c05feb85625f815b5d4e041d93","abstract_canon_sha256":"aa8b3918ded87f10e0f810c18d3822d066efb61bba87fc041410710bb15ac48d"},"schema_version":"1.0"},"canonical_sha256":"8c9fcf1df33bc7d486ed0d6da427becbbd8b9c0473b0743c4ab3df8d2baeb7e3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:02.386499Z","signature_b64":"LkcNylD/XUGzb8uYuqg6zlFcir6ss8ThL5EhGYXBFv8HBzYT5o/IfCAzLYdiqL6Sjcl0x489CSZEmM5ckgsFDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c9fcf1df33bc7d486ed0d6da427becbbd8b9c0473b0743c4ab3df8d2baeb7e3","last_reissued_at":"2026-07-05T08:32:02.385901Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:02.385901Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.09950","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":"2026-07-05T08:32:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J1g+IufMUpWBhlUNPkomx9RL6bvvXW0kfJ6ZQtT0eMXsBhlQIGksKpYGOd0pn5pzw8CyLQb+ejOSq5evsAJrAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T11:49:31.478849Z"},"content_sha256":"adebe7c16b87634fbd5dd6c8c10bc5801a0eca7190b442a54d12f52aaa80fc03","schema_version":"1.0","event_id":"sha256:adebe7c16b87634fbd5dd6c8c10bc5801a0eca7190b442a54d12f52aaa80fc03"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:RSP46HPTHPD5JBXNBVW2IJ56ZO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An efficient text augmentation approach for contextualized Mandarin speech recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Kai Liu, Naijun Zheng, Xucheng Wan, Zhou Huan, Ziqing Du","submitted_at":"2024-06-14T11:53:14Z","abstract_excerpt":"Although contextualized automatic speech recognition (ASR) systems are commonly used to improve the recognition of uncommon words, their effectiveness is hindered by the inherent limitations of speech-text data availability. To address this challenge, our study proposes to leverage extensive text-only datasets and contextualize pre-trained ASR models using a straightforward text-augmentation (TA) technique, all while keeping computational costs minimal. In particular, to contextualize a pre-trained CIF-based ASR, we construct a codebook using limited speech-text data. By utilizing a simple cod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09950","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/2406.09950/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":"2026-07-05T08:32:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v8VYuAGHWRXOGM3ZYO6riXv62AEtnTEnWtHlMFP64fis1JdfL/3uLs7R5LH2AkDJYJSAbCXAbjPeq0bF8z3aDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T11:49:31.479231Z"},"content_sha256":"2d51ebdef194cc9142a381033ad8527bf694793cedfff8a74dc2de1203d640a5","schema_version":"1.0","event_id":"sha256:2d51ebdef194cc9142a381033ad8527bf694793cedfff8a74dc2de1203d640a5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RSP46HPTHPD5JBXNBVW2IJ56ZO/bundle.json","state_url":"https://pith.science/pith/RSP46HPTHPD5JBXNBVW2IJ56ZO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RSP46HPTHPD5JBXNBVW2IJ56ZO/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":"2026-07-13T11:49:31Z","links":{"resolver":"https://pith.science/pith/RSP46HPTHPD5JBXNBVW2IJ56ZO","bundle":"https://pith.science/pith/RSP46HPTHPD5JBXNBVW2IJ56ZO/bundle.json","state":"https://pith.science/pith/RSP46HPTHPD5JBXNBVW2IJ56ZO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RSP46HPTHPD5JBXNBVW2IJ56ZO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RSP46HPTHPD5JBXNBVW2IJ56ZO","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":"aa8b3918ded87f10e0f810c18d3822d066efb61bba87fc041410710bb15ac48d","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-06-14T11:53:14Z","title_canon_sha256":"cb615d5bf8e45cfc529cc53b62ca82b45aa182c05feb85625f815b5d4e041d93"},"schema_version":"1.0","source":{"id":"2406.09950","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.09950","created_at":"2026-07-05T08:32:02Z"},{"alias_kind":"arxiv_version","alias_value":"2406.09950v1","created_at":"2026-07-05T08:32:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09950","created_at":"2026-07-05T08:32:02Z"},{"alias_kind":"pith_short_12","alias_value":"RSP46HPTHPD5","created_at":"2026-07-05T08:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"RSP46HPTHPD5JBXN","created_at":"2026-07-05T08:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"RSP46HPT","created_at":"2026-07-05T08:32:02Z"}],"graph_snapshots":[{"event_id":"sha256:2d51ebdef194cc9142a381033ad8527bf694793cedfff8a74dc2de1203d640a5","target":"graph","created_at":"2026-07-05T08:32:02Z","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/2406.09950/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Although contextualized automatic speech recognition (ASR) systems are commonly used to improve the recognition of uncommon words, their effectiveness is hindered by the inherent limitations of speech-text data availability. To address this challenge, our study proposes to leverage extensive text-only datasets and contextualize pre-trained ASR models using a straightforward text-augmentation (TA) technique, all while keeping computational costs minimal. In particular, to contextualize a pre-trained CIF-based ASR, we construct a codebook using limited speech-text data. By utilizing a simple cod","authors_text":"Kai Liu, Naijun Zheng, Xucheng Wan, Zhou Huan, Ziqing Du","cross_cats":["cs.CL","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-06-14T11:53:14Z","title":"An efficient text augmentation approach for contextualized Mandarin speech recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09950","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:adebe7c16b87634fbd5dd6c8c10bc5801a0eca7190b442a54d12f52aaa80fc03","target":"record","created_at":"2026-07-05T08:32:02Z","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":"aa8b3918ded87f10e0f810c18d3822d066efb61bba87fc041410710bb15ac48d","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-06-14T11:53:14Z","title_canon_sha256":"cb615d5bf8e45cfc529cc53b62ca82b45aa182c05feb85625f815b5d4e041d93"},"schema_version":"1.0","source":{"id":"2406.09950","kind":"arxiv","version":1}},"canonical_sha256":"8c9fcf1df33bc7d486ed0d6da427becbbd8b9c0473b0743c4ab3df8d2baeb7e3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8c9fcf1df33bc7d486ed0d6da427becbbd8b9c0473b0743c4ab3df8d2baeb7e3","first_computed_at":"2026-07-05T08:32:02.385901Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:32:02.385901Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LkcNylD/XUGzb8uYuqg6zlFcir6ss8ThL5EhGYXBFv8HBzYT5o/IfCAzLYdiqL6Sjcl0x489CSZEmM5ckgsFDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:32:02.386499Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.09950","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:adebe7c16b87634fbd5dd6c8c10bc5801a0eca7190b442a54d12f52aaa80fc03","sha256:2d51ebdef194cc9142a381033ad8527bf694793cedfff8a74dc2de1203d640a5"],"state_sha256":"0b9e0da47adf14b7f4df84ba8ee88c84367b966e4099d1f27fe0fe385c7e86bf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l81qw46h1KcERp5YLvzPQsrsJ7Uboaw2Don/f9dA9TgkMLvRex/ZO6VYG0N8OXxv+yURZyg/7E4i3qF6ti94AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-13T11:49:31.481242Z","bundle_sha256":"498f2ed3ebb79b251c56235348966c64e47f788953a7f71709d24093ab5e7f00"}}