{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:ITMF3YH572BPRAUXKX6UA6GE4U","short_pith_number":"pith:ITMF3YH5","canonical_record":{"source":{"id":"2212.01992","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-05T02:52:21Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"196700254e7bc807da6b101fd0f3947d10ca182158836ce1735e4a1ef90d2baa","abstract_canon_sha256":"9c69736dea9186b638c7ebcdb91cb4d1f7e3e82b6dc568377d4a769f3334a158"},"schema_version":"1.0"},"canonical_sha256":"44d85de0fdfe82f8829755fd4078c4e51f2419a08d3d9943bea1c51b2433d541","source":{"kind":"arxiv","id":"2212.01992","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.01992","created_at":"2026-07-05T05:44:51Z"},{"alias_kind":"arxiv_version","alias_value":"2212.01992v2","created_at":"2026-07-05T05:44:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.01992","created_at":"2026-07-05T05:44:51Z"},{"alias_kind":"pith_short_12","alias_value":"ITMF3YH572BP","created_at":"2026-07-05T05:44:51Z"},{"alias_kind":"pith_short_16","alias_value":"ITMF3YH572BPRAUX","created_at":"2026-07-05T05:44:51Z"},{"alias_kind":"pith_short_8","alias_value":"ITMF3YH5","created_at":"2026-07-05T05:44:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:ITMF3YH572BPRAUXKX6UA6GE4U","target":"record","payload":{"canonical_record":{"source":{"id":"2212.01992","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-05T02:52:21Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"196700254e7bc807da6b101fd0f3947d10ca182158836ce1735e4a1ef90d2baa","abstract_canon_sha256":"9c69736dea9186b638c7ebcdb91cb4d1f7e3e82b6dc568377d4a769f3334a158"},"schema_version":"1.0"},"canonical_sha256":"44d85de0fdfe82f8829755fd4078c4e51f2419a08d3d9943bea1c51b2433d541","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:44:51.810224Z","signature_b64":"RJDT70GdKvLaVHgOW83XZennHikF8/pDxh2AehWk5izz0dLY+S4Ya9UbKpVUP7fFVaeokUaMawXz/0LYTwsECA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"44d85de0fdfe82f8829755fd4078c4e51f2419a08d3d9943bea1c51b2433d541","last_reissued_at":"2026-07-05T05:44:51.809853Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:44:51.809853Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2212.01992","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":"2026-07-05T05:44:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Vi/e7aIsmW+zC7E8n34vRfD8UiM7zqqyP3iAqbyYrOMrv0m/QNpICn+WP437FGP8UcsGrS45uu4qwPA4Sr6kCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T04:18:09.519073Z"},"content_sha256":"6aef468d6c9470d0f2e62579f8887db6eeda0d764d4513c5cc0b3a8cf44c954e","schema_version":"1.0","event_id":"sha256:6aef468d6c9470d0f2e62579f8887db6eeda0d764d4513c5cc0b3a8cf44c954e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:ITMF3YH572BPRAUXKX6UA6GE4U","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fast and accurate factorized neural transducer for text adaption of end-to-end speech recognition models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Jian Xue, Jinyu Li, Partha Parthasarathy, Rui Zhao, Veljko Miljanic","submitted_at":"2022-12-05T02:52:21Z","abstract_excerpt":"Neural transducer is now the most popular end-to-end model for speech recognition, due to its naturally streaming ability. However, it is challenging to adapt it with text-only data. Factorized neural transducer (FNT) model was proposed to mitigate this problem. The improved adaptation ability of FNT on text-only adaptation data came at the cost of lowered accuracy compared to the standard neural transducer model. We propose several methods to improve the performance of the FNT model. They are: adding CTC criterion during training, adding KL divergence loss during adaptation, using a pre-train"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.01992","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/2212.01992/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":"2026-07-05T05:44:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ThNjZRPkB+0XsIRdu8MifZJs81ICcLWzNxvheeqJsuCPgbrEdahcbJqZ9hJlMuRhSUwDDQVk1xljj2Q4FEoxCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T04:18:09.520119Z"},"content_sha256":"d4973d774e592a2c5f2678d8e881828861fbb4453e21ed437f841eb8e122c9e7","schema_version":"1.0","event_id":"sha256:d4973d774e592a2c5f2678d8e881828861fbb4453e21ed437f841eb8e122c9e7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ITMF3YH572BPRAUXKX6UA6GE4U/bundle.json","state_url":"https://pith.science/pith/ITMF3YH572BPRAUXKX6UA6GE4U/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ITMF3YH572BPRAUXKX6UA6GE4U/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":"2026-08-05T04:18:09Z","links":{"resolver":"https://pith.science/pith/ITMF3YH572BPRAUXKX6UA6GE4U","bundle":"https://pith.science/pith/ITMF3YH572BPRAUXKX6UA6GE4U/bundle.json","state":"https://pith.science/pith/ITMF3YH572BPRAUXKX6UA6GE4U/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ITMF3YH572BPRAUXKX6UA6GE4U/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:ITMF3YH572BPRAUXKX6UA6GE4U","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":"9c69736dea9186b638c7ebcdb91cb4d1f7e3e82b6dc568377d4a769f3334a158","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-05T02:52:21Z","title_canon_sha256":"196700254e7bc807da6b101fd0f3947d10ca182158836ce1735e4a1ef90d2baa"},"schema_version":"1.0","source":{"id":"2212.01992","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.01992","created_at":"2026-07-05T05:44:51Z"},{"alias_kind":"arxiv_version","alias_value":"2212.01992v2","created_at":"2026-07-05T05:44:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.01992","created_at":"2026-07-05T05:44:51Z"},{"alias_kind":"pith_short_12","alias_value":"ITMF3YH572BP","created_at":"2026-07-05T05:44:51Z"},{"alias_kind":"pith_short_16","alias_value":"ITMF3YH572BPRAUX","created_at":"2026-07-05T05:44:51Z"},{"alias_kind":"pith_short_8","alias_value":"ITMF3YH5","created_at":"2026-07-05T05:44:51Z"}],"graph_snapshots":[{"event_id":"sha256:d4973d774e592a2c5f2678d8e881828861fbb4453e21ed437f841eb8e122c9e7","target":"graph","created_at":"2026-07-05T05:44:51Z","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/2212.01992/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Neural transducer is now the most popular end-to-end model for speech recognition, due to its naturally streaming ability. However, it is challenging to adapt it with text-only data. Factorized neural transducer (FNT) model was proposed to mitigate this problem. The improved adaptation ability of FNT on text-only adaptation data came at the cost of lowered accuracy compared to the standard neural transducer model. We propose several methods to improve the performance of the FNT model. They are: adding CTC criterion during training, adding KL divergence loss during adaptation, using a pre-train","authors_text":"Jian Xue, Jinyu Li, Partha Parthasarathy, Rui Zhao, Veljko Miljanic","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-05T02:52:21Z","title":"Fast and accurate factorized neural transducer for text adaption of end-to-end speech recognition models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.01992","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":"sha256:6aef468d6c9470d0f2e62579f8887db6eeda0d764d4513c5cc0b3a8cf44c954e","target":"record","created_at":"2026-07-05T05:44:51Z","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":"9c69736dea9186b638c7ebcdb91cb4d1f7e3e82b6dc568377d4a769f3334a158","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-05T02:52:21Z","title_canon_sha256":"196700254e7bc807da6b101fd0f3947d10ca182158836ce1735e4a1ef90d2baa"},"schema_version":"1.0","source":{"id":"2212.01992","kind":"arxiv","version":2}},"canonical_sha256":"44d85de0fdfe82f8829755fd4078c4e51f2419a08d3d9943bea1c51b2433d541","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"44d85de0fdfe82f8829755fd4078c4e51f2419a08d3d9943bea1c51b2433d541","first_computed_at":"2026-07-05T05:44:51.809853Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:44:51.809853Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RJDT70GdKvLaVHgOW83XZennHikF8/pDxh2AehWk5izz0dLY+S4Ya9UbKpVUP7fFVaeokUaMawXz/0LYTwsECA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:44:51.810224Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.01992","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6aef468d6c9470d0f2e62579f8887db6eeda0d764d4513c5cc0b3a8cf44c954e","sha256:d4973d774e592a2c5f2678d8e881828861fbb4453e21ed437f841eb8e122c9e7"],"state_sha256":"8047db9a0952db16b10aeb2ac19046e897508a1316a114c182875a6d3af97264"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dqkHrK1hXfCznIJOJq2MihAfXeE9P/TxjOBDePxeyvdpkpqoMfbwzIOAWuuuD2zo5gixpE6rEuGqTEV4co7nAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T04:18:09.527761Z","bundle_sha256":"e666bad59492f5a412a1015249a5fdbb8df8350c0d36d938ca8e4ea0e4874ad5"}}