{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:GAF6LT4N6C76XVACGU4PF4HMBZ","short_pith_number":"pith:GAF6LT4N","schema_version":"1.0","canonical_sha256":"300be5cf8df0bfebd4023538f2f0ec0e47e9f89d0ab01d3d923ee345868a232d","source":{"kind":"arxiv","id":"2210.00077","version":2},"attestation_state":"computed","paper":{"title":"E-Branchformer: Branchformer with Enhanced merging for speech recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"eess.AS","authors_text":"Felix Wu, Jing Pan, Kwangyoun Kim, Kyu J. Han, Prashant Sridhar, Shinji Watanabe, Yifan Peng","submitted_at":"2022-09-30T20:22:15Z","abstract_excerpt":"Conformer, combining convolution and self-attention sequentially to capture both local and global information, has shown remarkable performance and is currently regarded as the state-of-the-art for automatic speech recognition (ASR). Several other studies have explored integrating convolution and self-attention but they have not managed to match Conformer's performance. The recently introduced Branchformer achieves comparable performance to Conformer by using dedicated branches of convolution and self-attention and merging local and global context from each branch. In this paper, we propose E-"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2210.00077","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-09-30T20:22:15Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4d5df09367a63c387369b82c08b2c490f115eac4fa1b0edd3a88dce61558c99d","abstract_canon_sha256":"bef749a3a627c7ebe4442f57f8e14616b775fcd7d8bfbb5db84376ef212b2940"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:07:04.098822Z","signature_b64":"qdg0c0EL9jBr7l4TZJLuKOTcNoxgUKkXgQXc6gvtYyULxSvK/gV4LKhJUN2GESH/+f1TZzTnDbPkthpKt2XIAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"300be5cf8df0bfebd4023538f2f0ec0e47e9f89d0ab01d3d923ee345868a232d","last_reissued_at":"2026-07-05T05:07:04.098400Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:07:04.098400Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"E-Branchformer: Branchformer with Enhanced merging for speech recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"eess.AS","authors_text":"Felix Wu, Jing Pan, Kwangyoun Kim, Kyu J. Han, Prashant Sridhar, Shinji Watanabe, Yifan Peng","submitted_at":"2022-09-30T20:22:15Z","abstract_excerpt":"Conformer, combining convolution and self-attention sequentially to capture both local and global information, has shown remarkable performance and is currently regarded as the state-of-the-art for automatic speech recognition (ASR). Several other studies have explored integrating convolution and self-attention but they have not managed to match Conformer's performance. The recently introduced Branchformer achieves comparable performance to Conformer by using dedicated branches of convolution and self-attention and merging local and global context from each branch. In this paper, we propose E-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.00077","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/2210.00077/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2210.00077","created_at":"2026-07-05T05:07:04.098457+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.00077v2","created_at":"2026-07-05T05:07:04.098457+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.00077","created_at":"2026-07-05T05:07:04.098457+00:00"},{"alias_kind":"pith_short_12","alias_value":"GAF6LT4N6C76","created_at":"2026-07-05T05:07:04.098457+00:00"},{"alias_kind":"pith_short_16","alias_value":"GAF6LT4N6C76XVAC","created_at":"2026-07-05T05:07:04.098457+00:00"},{"alias_kind":"pith_short_8","alias_value":"GAF6LT4N","created_at":"2026-07-05T05:07:04.098457+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22824","citing_title":"BranchShine: Compact Raw-Audio-to-IPA Transcription with a RoPE E-Branchformer Encoder","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GAF6LT4N6C76XVACGU4PF4HMBZ","json":"https://pith.science/pith/GAF6LT4N6C76XVACGU4PF4HMBZ.json","graph_json":"https://pith.science/api/pith-number/GAF6LT4N6C76XVACGU4PF4HMBZ/graph.json","events_json":"https://pith.science/api/pith-number/GAF6LT4N6C76XVACGU4PF4HMBZ/events.json","paper":"https://pith.science/paper/GAF6LT4N"},"agent_actions":{"view_html":"https://pith.science/pith/GAF6LT4N6C76XVACGU4PF4HMBZ","download_json":"https://pith.science/pith/GAF6LT4N6C76XVACGU4PF4HMBZ.json","view_paper":"https://pith.science/paper/GAF6LT4N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.00077&json=true","fetch_graph":"https://pith.science/api/pith-number/GAF6LT4N6C76XVACGU4PF4HMBZ/graph.json","fetch_events":"https://pith.science/api/pith-number/GAF6LT4N6C76XVACGU4PF4HMBZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GAF6LT4N6C76XVACGU4PF4HMBZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GAF6LT4N6C76XVACGU4PF4HMBZ/action/storage_attestation","attest_author":"https://pith.science/pith/GAF6LT4N6C76XVACGU4PF4HMBZ/action/author_attestation","sign_citation":"https://pith.science/pith/GAF6LT4N6C76XVACGU4PF4HMBZ/action/citation_signature","submit_replication":"https://pith.science/pith/GAF6LT4N6C76XVACGU4PF4HMBZ/action/replication_record"}},"created_at":"2026-07-05T05:07:04.098457+00:00","updated_at":"2026-07-05T05:07:04.098457+00:00"}