{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:TIDO3KDLQCHY3Q7SSLJLZQFCUJ","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":"0c6f1163aebb7ec58af3786f7c15e8f05f080899a4dbf4898735a9f00999c54a","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-11-17T08:48:27Z","title_canon_sha256":"1b27a89de04e8956a532c39aaad1b295fc61793022faedb3ad1652223cbc4ba0"},"schema_version":"1.0","source":{"id":"2211.09412","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.09412","created_at":"2026-07-05T05:16:55Z"},{"alias_kind":"arxiv_version","alias_value":"2211.09412v1","created_at":"2026-07-05T05:16:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.09412","created_at":"2026-07-05T05:16:55Z"},{"alias_kind":"pith_short_12","alias_value":"TIDO3KDLQCHY","created_at":"2026-07-05T05:16:55Z"},{"alias_kind":"pith_short_16","alias_value":"TIDO3KDLQCHY3Q7S","created_at":"2026-07-05T05:16:55Z"},{"alias_kind":"pith_short_8","alias_value":"TIDO3KDL","created_at":"2026-07-05T05:16:55Z"}],"graph_snapshots":[{"event_id":"sha256:ad4f13cdd22bc67ded1a1e11f673a0c7df645e0bbb45b77de4fa8ef8c42dba37","target":"graph","created_at":"2026-07-05T05:16:55Z","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/2211.09412/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Traditional automatic speech recognition~(ASR) systems usually focus on individual utterances, without considering long-form speech with useful historical information, which is more practical in real scenarios. Simply attending longer transcription history for a vanilla neural transducer model shows no much gain in our preliminary experiments, since the prediction network is not a pure language model. This motivates us to leverage the factorized neural transducer structure, containing a real language model, the vocabulary predictor. We propose the {LongFNT-Text} architecture, which fuses the s","authors_text":"Jinyu Li, Rui Zhao, Shujie Liu, Xie Chen, Xun Gong, Yanmin Qian, Yu Wu","cross_cats":["cs.CL","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-11-17T08:48:27Z","title":"LongFNT: Long-form Speech Recognition with Factorized Neural Transducer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.09412","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":"sha256:5f1f51c47e55989188a64130e93ac4221966dd72aaeb2c11e7433d8654e87433","target":"record","created_at":"2026-07-05T05:16:55Z","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":"0c6f1163aebb7ec58af3786f7c15e8f05f080899a4dbf4898735a9f00999c54a","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-11-17T08:48:27Z","title_canon_sha256":"1b27a89de04e8956a532c39aaad1b295fc61793022faedb3ad1652223cbc4ba0"},"schema_version":"1.0","source":{"id":"2211.09412","kind":"arxiv","version":1}},"canonical_sha256":"9a06eda86b808f8dc3f292d2bcc0a2a27de49c2b2097ba10a20b053c7bee6522","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9a06eda86b808f8dc3f292d2bcc0a2a27de49c2b2097ba10a20b053c7bee6522","first_computed_at":"2026-07-05T05:16:55.733476Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:16:55.733476Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KQGKPV+vtfNXB1bYBFhjRKFrETALXmYZFhqkl58tuWp+eu88+Qmdjo65F99lD3otmllDxbA5L6vKagrhy5ehCA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:16:55.733865Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.09412","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5f1f51c47e55989188a64130e93ac4221966dd72aaeb2c11e7433d8654e87433","sha256:ad4f13cdd22bc67ded1a1e11f673a0c7df645e0bbb45b77de4fa8ef8c42dba37"],"state_sha256":"db0f9cb781e7c8253b835ddbdc29b0de44466621429454417d2b814742ea121d"}