{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:TEQIJJ3BD25KWXT5JVZLCYPDGS","short_pith_number":"pith:TEQIJJ3B","schema_version":"1.0","canonical_sha256":"992084a7611ebaab5e7d4d72b161e334a1064562a5521accd8e55ecdfdb2fd81","source":{"kind":"arxiv","id":"1905.11235","version":4},"attestation_state":"computed","paper":{"title":"CIF: Continuous Integrate-and-Fire for End-to-End Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Bo Xu, Linhao Dong","submitted_at":"2019-05-27T14:00:45Z","abstract_excerpt":"In this paper, we propose a novel soft and monotonic alignment mechanism used for sequence transduction. It is inspired by the integrate-and-fire model in spiking neural networks and employed in the encoder-decoder framework consists of continuous functions, thus being named as: Continuous Integrate-and-Fire (CIF). Applied to the ASR task, CIF not only shows a concise calculation, but also supports online recognition and acoustic boundary positioning, thus suitable for various ASR scenarios. Several support strategies are also proposed to alleviate the unique problems of CIF-based model. With "},"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":"1905.11235","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-27T14:00:45Z","cross_cats_sorted":["cs.LG","cs.NE","cs.SD","eess.AS"],"title_canon_sha256":"8ff3430a065d78eee8a670a857f3d3d160409cb4d9875aa82ea9e1e5616cc9cf","abstract_canon_sha256":"bb75c323aeadaef0a9a0cc0c4ffb1d5d03d10622c1d68dc2081e23fb4556167a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:40:13.637127Z","signature_b64":"q2FRceod8P6GcMPPABFMUhPeueBAM5+qnLvqCPUh3v0JbByhkgWTGxmqqrq+ZbgSo/zS5nYLC4hLEBfaq9iuBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"992084a7611ebaab5e7d4d72b161e334a1064562a5521accd8e55ecdfdb2fd81","last_reissued_at":"2026-07-05T00:40:13.636711Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:40:13.636711Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CIF: Continuous Integrate-and-Fire for End-to-End Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Bo Xu, Linhao Dong","submitted_at":"2019-05-27T14:00:45Z","abstract_excerpt":"In this paper, we propose a novel soft and monotonic alignment mechanism used for sequence transduction. It is inspired by the integrate-and-fire model in spiking neural networks and employed in the encoder-decoder framework consists of continuous functions, thus being named as: Continuous Integrate-and-Fire (CIF). Applied to the ASR task, CIF not only shows a concise calculation, but also supports online recognition and acoustic boundary positioning, thus suitable for various ASR scenarios. Several support strategies are also proposed to alleviate the unique problems of CIF-based model. With "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.11235","kind":"arxiv","version":4},"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/1905.11235/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":"1905.11235","created_at":"2026-07-05T00:40:13.636768+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.11235v4","created_at":"2026-07-05T00:40:13.636768+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.11235","created_at":"2026-07-05T00:40:13.636768+00:00"},{"alias_kind":"pith_short_12","alias_value":"TEQIJJ3BD25K","created_at":"2026-07-05T00:40:13.636768+00:00"},{"alias_kind":"pith_short_16","alias_value":"TEQIJJ3BD25KWXT5","created_at":"2026-07-05T00:40:13.636768+00:00"},{"alias_kind":"pith_short_8","alias_value":"TEQIJJ3B","created_at":"2026-07-05T00:40:13.636768+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.17537","citing_title":"Towards Maximum Likelihood Training for Transducer-based Streaming Speech Recognition","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TEQIJJ3BD25KWXT5JVZLCYPDGS","json":"https://pith.science/pith/TEQIJJ3BD25KWXT5JVZLCYPDGS.json","graph_json":"https://pith.science/api/pith-number/TEQIJJ3BD25KWXT5JVZLCYPDGS/graph.json","events_json":"https://pith.science/api/pith-number/TEQIJJ3BD25KWXT5JVZLCYPDGS/events.json","paper":"https://pith.science/paper/TEQIJJ3B"},"agent_actions":{"view_html":"https://pith.science/pith/TEQIJJ3BD25KWXT5JVZLCYPDGS","download_json":"https://pith.science/pith/TEQIJJ3BD25KWXT5JVZLCYPDGS.json","view_paper":"https://pith.science/paper/TEQIJJ3B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.11235&json=true","fetch_graph":"https://pith.science/api/pith-number/TEQIJJ3BD25KWXT5JVZLCYPDGS/graph.json","fetch_events":"https://pith.science/api/pith-number/TEQIJJ3BD25KWXT5JVZLCYPDGS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TEQIJJ3BD25KWXT5JVZLCYPDGS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TEQIJJ3BD25KWXT5JVZLCYPDGS/action/storage_attestation","attest_author":"https://pith.science/pith/TEQIJJ3BD25KWXT5JVZLCYPDGS/action/author_attestation","sign_citation":"https://pith.science/pith/TEQIJJ3BD25KWXT5JVZLCYPDGS/action/citation_signature","submit_replication":"https://pith.science/pith/TEQIJJ3BD25KWXT5JVZLCYPDGS/action/replication_record"}},"created_at":"2026-07-05T00:40:13.636768+00:00","updated_at":"2026-07-05T00:40:13.636768+00:00"}