{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:O5BV2L5HLNERROO4ANZ3I7K34J","short_pith_number":"pith:O5BV2L5H","canonical_record":{"source":{"id":"2506.03722","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T08:53:40Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"3b35ad3de1d692eb8379be7b7124fa2da14bbe0db6281e2dde80744e7bb327d7","abstract_canon_sha256":"cd342a4303d83b2190084d4056e69a4db62ac22d3ef8ed9a850dd18ce60020b1"},"schema_version":"1.0"},"canonical_sha256":"77435d2fa75b4918b9dc0373b47d5be26404b8356d15b2cb73db486e7e0df542","source":{"kind":"arxiv","id":"2506.03722","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:O5BV2L5HLNERROO4ANZ3I7K34J","target":"record","payload":{"canonical_record":{"source":{"id":"2506.03722","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T08:53:40Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"3b35ad3de1d692eb8379be7b7124fa2da14bbe0db6281e2dde80744e7bb327d7","abstract_canon_sha256":"cd342a4303d83b2190084d4056e69a4db62ac22d3ef8ed9a850dd18ce60020b1"},"schema_version":"1.0"},"canonical_sha256":"77435d2fa75b4918b9dc0373b47d5be26404b8356d15b2cb73db486e7e0df542","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:50.726117Z","signature_b64":"+a3EmK7tIpshr68QNsFlY9ghujvaPSB4VsdAuUmhKo5yT3CyGrJ9Wcg59fQ4u9+P6enh+Rulw28Cwo02Tft3AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"77435d2fa75b4918b9dc0373b47d5be26404b8356d15b2cb73db486e7e0df542","last_reissued_at":"2026-07-05T11:15:50.725513Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:50.725513Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.03722","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:15:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x06VTVGNHtomc8CINCWAa+fFm+Iww7tktx76dq5haTxTW5h1O9wEm07+wgfEJWfH03GO4wlLRS+PaEwF56EVCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T04:04:40.891527Z"},"content_sha256":"ea2671cd24aca68773f214aee65cf6ef987dfbd3fba88ccd5ea1e9711fc1c7fd","schema_version":"1.0","event_id":"sha256:ea2671cd24aca68773f214aee65cf6ef987dfbd3fba88ccd5ea1e9711fc1c7fd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:O5BV2L5HLNERROO4ANZ3I7K34J","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MFLA: Monotonic Finite Look-ahead Attention for Streaming Speech Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Chenyang Le, Huiyan Li, Manhong Wang, Xingyang Ma, Yanmin Qian, Yinfeng Xia, Yutao Sun","submitted_at":"2025-06-04T08:53:40Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.03722","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/2506.03722/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:15:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BFo53yTRXmDYi4d2RQq/vx7KbRazrRMbJrmTuM4nVPL0nRBf6+uhKlh7IpSJJWqCoae98Sc6J/kkdOwFKgDUCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T04:04:40.892062Z"},"content_sha256":"0fe0b83fd5b58b24db1e5c9ee40df9b06c966a2db36cd36ddb08e92da3a360e9","schema_version":"1.0","event_id":"sha256:0fe0b83fd5b58b24db1e5c9ee40df9b06c966a2db36cd36ddb08e92da3a360e9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/O5BV2L5HLNERROO4ANZ3I7K34J/bundle.json","state_url":"https://pith.science/pith/O5BV2L5HLNERROO4ANZ3I7K34J/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/O5BV2L5HLNERROO4ANZ3I7K34J/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T04:04:40Z","links":{"resolver":"https://pith.science/pith/O5BV2L5HLNERROO4ANZ3I7K34J","bundle":"https://pith.science/pith/O5BV2L5HLNERROO4ANZ3I7K34J/bundle.json","state":"https://pith.science/pith/O5BV2L5HLNERROO4ANZ3I7K34J/state.json","well_known_bundle":"https://pith.science/.well-known/pith/O5BV2L5HLNERROO4ANZ3I7K34J/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1c40xweql9GZE6SndnNHWSUZIpflMhrpD5AnSGNmzqITlrNdXB0jz2kidue21CR/RNYvOxAmhMtezQ+0MZv8CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T04:04:40.895739Z","bundle_sha256":"f34ab441c6e69ffc5784db9a6c5125e57a22aff8643390eb5090f68c05455662"}}