{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:O5BV2L5HLNERROO4ANZ3I7K34J","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":"cd342a4303d83b2190084d4056e69a4db62ac22d3ef8ed9a850dd18ce60020b1","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T08:53:40Z","title_canon_sha256":"3b35ad3de1d692eb8379be7b7124fa2da14bbe0db6281e2dde80744e7bb327d7"},"schema_version":"1.0","source":{"id":"2506.03722","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.03722","created_at":"2026-07-05T11:15:50Z"},{"alias_kind":"arxiv_version","alias_value":"2506.03722v1","created_at":"2026-07-05T11:15:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.03722","created_at":"2026-07-05T11:15:50Z"},{"alias_kind":"pith_short_12","alias_value":"O5BV2L5HLNER","created_at":"2026-07-05T11:15:50Z"},{"alias_kind":"pith_short_16","alias_value":"O5BV2L5HLNERROO4","created_at":"2026-07-05T11:15:50Z"},{"alias_kind":"pith_short_8","alias_value":"O5BV2L5H","created_at":"2026-07-05T11:15:50Z"}],"graph_snapshots":[{"event_id":"sha256:0fe0b83fd5b58b24db1e5c9ee40df9b06c966a2db36cd36ddb08e92da3a360e9","target":"graph","created_at":"2026-07-05T11:15:50Z","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/2506.03722/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Applying large pre-trained speech models like Whisper has shown promise in reducing training costs for various speech tasks. However, integrating these models into streaming systems remains a challenge. This paper presents a novel prefix-to-prefix training framework for streaming recognition by fine-tuning the Whisper. We introduce the Continuous Integrate-and-Fire mechanism to establish a quasi-monotonic alignment between continuous speech sequences and discrete text tokens. Additionally, we design Monotonic Finite Look-ahead Attention, allowing each token to attend to infinite left-context a","authors_text":"Chenyang Le, Huiyan Li, Manhong Wang, Xingyang Ma, Yanmin Qian, Yinfeng Xia, Yutao Sun","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T08:53:40Z","title":"MFLA: Monotonic Finite Look-ahead Attention for Streaming Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.03722","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:ea2671cd24aca68773f214aee65cf6ef987dfbd3fba88ccd5ea1e9711fc1c7fd","target":"record","created_at":"2026-07-05T11:15:50Z","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":"cd342a4303d83b2190084d4056e69a4db62ac22d3ef8ed9a850dd18ce60020b1","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T08:53:40Z","title_canon_sha256":"3b35ad3de1d692eb8379be7b7124fa2da14bbe0db6281e2dde80744e7bb327d7"},"schema_version":"1.0","source":{"id":"2506.03722","kind":"arxiv","version":1}},"canonical_sha256":"77435d2fa75b4918b9dc0373b47d5be26404b8356d15b2cb73db486e7e0df542","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"77435d2fa75b4918b9dc0373b47d5be26404b8356d15b2cb73db486e7e0df542","first_computed_at":"2026-07-05T11:15:50.725513Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:50.725513Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+a3EmK7tIpshr68QNsFlY9ghujvaPSB4VsdAuUmhKo5yT3CyGrJ9Wcg59fQ4u9+P6enh+Rulw28Cwo02Tft3AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:50.726117Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.03722","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ea2671cd24aca68773f214aee65cf6ef987dfbd3fba88ccd5ea1e9711fc1c7fd","sha256:0fe0b83fd5b58b24db1e5c9ee40df9b06c966a2db36cd36ddb08e92da3a360e9"],"state_sha256":"adc8120c9fdddcbb2451534bd5ea39555cd5a016d26dea39b54e1196788abc6a"}