{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:6DHRS2EVRXDZU252EMXICQOSMQ","short_pith_number":"pith:6DHRS2EV","schema_version":"1.0","canonical_sha256":"f0cf1968958dc79a6bba232e8141d264291f0429bc3d4d09f7aa8dc300b91540","source":{"kind":"arxiv","id":"2106.09236","version":1},"attestation_state":"computed","paper":{"title":"Efficient Conformer with Prob-Sparse Attention Mechanism for End-to-EndSpeech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Lei Xie, Long Ma, Sining Sun, Xiong Wang","submitted_at":"2021-06-17T04:04:04Z","abstract_excerpt":"End-to-end models are favored in automatic speech recognition (ASR) because of their simplified system structure and superior performance. Among these models, Transformer and Conformer have achieved state-of-the-art recognition accuracy in which self-attention plays a vital role in capturing important global information. However, the time and memory complexity of self-attention increases squarely with the length of the sentence. In this paper, a prob-sparse self-attention mechanism is introduced into Conformer to sparse the computing process of self-attention in order to accelerate inference s"},"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":"2106.09236","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-06-17T04:04:04Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"1f956c869d0b5b3882ac20d94cac5313529ee28cb08ed33d4711cd93467d45e2","abstract_canon_sha256":"d784dc8c3765a894766ee160f2715c12d29ce3bbadd4f5fa6fa5e5969ad0b6c5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:50:13.959232Z","signature_b64":"cHk92vP3WF3UafLvFHQUfcuVgQU6+B72g5LzVjlbkNZlqAZDeVUbS+Vf0CXCmL4GGNI+ubIKYjObMf1Vl/huAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0cf1968958dc79a6bba232e8141d264291f0429bc3d4d09f7aa8dc300b91540","last_reissued_at":"2026-07-05T02:50:13.958823Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:50:13.958823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Conformer with Prob-Sparse Attention Mechanism for End-to-EndSpeech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Lei Xie, Long Ma, Sining Sun, Xiong Wang","submitted_at":"2021-06-17T04:04:04Z","abstract_excerpt":"End-to-end models are favored in automatic speech recognition (ASR) because of their simplified system structure and superior performance. Among these models, Transformer and Conformer have achieved state-of-the-art recognition accuracy in which self-attention plays a vital role in capturing important global information. However, the time and memory complexity of self-attention increases squarely with the length of the sentence. In this paper, a prob-sparse self-attention mechanism is introduced into Conformer to sparse the computing process of self-attention in order to accelerate inference s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.09236","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/2106.09236/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":"2106.09236","created_at":"2026-07-05T02:50:13.958878+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.09236v1","created_at":"2026-07-05T02:50:13.958878+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.09236","created_at":"2026-07-05T02:50:13.958878+00:00"},{"alias_kind":"pith_short_12","alias_value":"6DHRS2EVRXDZ","created_at":"2026-07-05T02:50:13.958878+00:00"},{"alias_kind":"pith_short_16","alias_value":"6DHRS2EVRXDZU252","created_at":"2026-07-05T02:50:13.958878+00:00"},{"alias_kind":"pith_short_8","alias_value":"6DHRS2EV","created_at":"2026-07-05T02:50:13.958878+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04833","citing_title":"Signed Dual Attention: Capturing Signed Dependencies in Time Series Forecasting","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6DHRS2EVRXDZU252EMXICQOSMQ","json":"https://pith.science/pith/6DHRS2EVRXDZU252EMXICQOSMQ.json","graph_json":"https://pith.science/api/pith-number/6DHRS2EVRXDZU252EMXICQOSMQ/graph.json","events_json":"https://pith.science/api/pith-number/6DHRS2EVRXDZU252EMXICQOSMQ/events.json","paper":"https://pith.science/paper/6DHRS2EV"},"agent_actions":{"view_html":"https://pith.science/pith/6DHRS2EVRXDZU252EMXICQOSMQ","download_json":"https://pith.science/pith/6DHRS2EVRXDZU252EMXICQOSMQ.json","view_paper":"https://pith.science/paper/6DHRS2EV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.09236&json=true","fetch_graph":"https://pith.science/api/pith-number/6DHRS2EVRXDZU252EMXICQOSMQ/graph.json","fetch_events":"https://pith.science/api/pith-number/6DHRS2EVRXDZU252EMXICQOSMQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6DHRS2EVRXDZU252EMXICQOSMQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6DHRS2EVRXDZU252EMXICQOSMQ/action/storage_attestation","attest_author":"https://pith.science/pith/6DHRS2EVRXDZU252EMXICQOSMQ/action/author_attestation","sign_citation":"https://pith.science/pith/6DHRS2EVRXDZU252EMXICQOSMQ/action/citation_signature","submit_replication":"https://pith.science/pith/6DHRS2EVRXDZU252EMXICQOSMQ/action/replication_record"}},"created_at":"2026-07-05T02:50:13.958878+00:00","updated_at":"2026-07-05T02:50:13.958878+00:00"}