{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:2KNTVW2SZFENQIKC7OB37VHFMS","short_pith_number":"pith:2KNTVW2S","canonical_record":{"source":{"id":"2407.04439","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-07-05T11:41:11Z","cross_cats_sorted":[],"title_canon_sha256":"e7004d6f3d7e712dd16c005b5504f093ed600d97994f15fff437cb6bee2f8169","abstract_canon_sha256":"661fab7655017d72c6c423aaec510b1939cb475480a01a220dbc90bd8300e630"},"schema_version":"1.0"},"canonical_sha256":"d29b3adb52c948d82142fb83bfd4e564ba43079431e9db325e364c35ba7e432f","source":{"kind":"arxiv","id":"2407.04439","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.04439","created_at":"2026-07-05T09:17:45Z"},{"alias_kind":"arxiv_version","alias_value":"2407.04439v2","created_at":"2026-07-05T09:17:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.04439","created_at":"2026-07-05T09:17:45Z"},{"alias_kind":"pith_short_12","alias_value":"2KNTVW2SZFEN","created_at":"2026-07-05T09:17:45Z"},{"alias_kind":"pith_short_16","alias_value":"2KNTVW2SZFENQIKC","created_at":"2026-07-05T09:17:45Z"},{"alias_kind":"pith_short_8","alias_value":"2KNTVW2S","created_at":"2026-07-05T09:17:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:2KNTVW2SZFENQIKC7OB37VHFMS","target":"record","payload":{"canonical_record":{"source":{"id":"2407.04439","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-07-05T11:41:11Z","cross_cats_sorted":[],"title_canon_sha256":"e7004d6f3d7e712dd16c005b5504f093ed600d97994f15fff437cb6bee2f8169","abstract_canon_sha256":"661fab7655017d72c6c423aaec510b1939cb475480a01a220dbc90bd8300e630"},"schema_version":"1.0"},"canonical_sha256":"d29b3adb52c948d82142fb83bfd4e564ba43079431e9db325e364c35ba7e432f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:17:45.178573Z","signature_b64":"+eRWNgWvKlxPA1qcuginAzKCOtEEiQVPSadPWlB2RRV5R8ZKGe06md57+7SCcVRdeaNs5wypBKN5cYfy5YmOBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d29b3adb52c948d82142fb83bfd4e564ba43079431e9db325e364c35ba7e432f","last_reissued_at":"2026-07-05T09:17:45.178095Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:17:45.178095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.04439","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:17:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4sC8fl8N1bf2+mYvaOYoaKLBxNX5K/AklebgGvUG9uSCcZwoq7uV2e3BvcgYoIWRqaTyEo9cfHXk5sW/jvaZCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:40:01.256103Z"},"content_sha256":"9cf2b02ad6df569997246eac582e36d43f436517963ea3cd0cd6e1ff10382433","schema_version":"1.0","event_id":"sha256:9cf2b02ad6df569997246eac582e36d43f436517963ea3cd0cd6e1ff10382433"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:2KNTVW2SZFENQIKC7OB37VHFMS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"XLSR-Transducer: Streaming ASR for Self-Supervised Pretrained Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Aravind Ganapathiraju, Esa\\'u Villatoro-Tello, Iuliia Thorbecke, Juan Zuluaga-Gomez, Manjunath K E, Petr Motlicek, Shashi Kumar, Srikanth Madikeri","submitted_at":"2024-07-05T11:41:11Z","abstract_excerpt":"Self-supervised pretrained models exhibit competitive performance in automatic speech recognition on finetuning, even with limited in-domain supervised data. However, popular pretrained models are not suitable for streaming ASR because they are trained with full attention context. In this paper, we introduce XLSR-Transducer, where the XLSR-53 model is used as encoder in transducer setup. Our experiments on the AMI dataset reveal that the XLSR-Transducer achieves 4% absolute WER improvement over Whisper large-v2 and 8% over a Zipformer transducer model trained from scratch. To enable streaming "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.04439","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/2407.04439/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":"2026-07-05T09:17:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Cgd0QfhLpX6RhshNQKgL4JkXcVbKvJpqVuvytrghwoW2JuixWSmCOMGEqn13Jbu/7Qo5bS117j7qHuM5U7NMAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:40:01.257150Z"},"content_sha256":"b24645c19686921c13394283d64c611b6dbf25b2d3d07a9424c0e320168a7e77","schema_version":"1.0","event_id":"sha256:b24645c19686921c13394283d64c611b6dbf25b2d3d07a9424c0e320168a7e77"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2KNTVW2SZFENQIKC7OB37VHFMS/bundle.json","state_url":"https://pith.science/pith/2KNTVW2SZFENQIKC7OB37VHFMS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2KNTVW2SZFENQIKC7OB37VHFMS/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":"2026-08-08T09:40:01Z","links":{"resolver":"https://pith.science/pith/2KNTVW2SZFENQIKC7OB37VHFMS","bundle":"https://pith.science/pith/2KNTVW2SZFENQIKC7OB37VHFMS/bundle.json","state":"https://pith.science/pith/2KNTVW2SZFENQIKC7OB37VHFMS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2KNTVW2SZFENQIKC7OB37VHFMS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2KNTVW2SZFENQIKC7OB37VHFMS","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":"661fab7655017d72c6c423aaec510b1939cb475480a01a220dbc90bd8300e630","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-07-05T11:41:11Z","title_canon_sha256":"e7004d6f3d7e712dd16c005b5504f093ed600d97994f15fff437cb6bee2f8169"},"schema_version":"1.0","source":{"id":"2407.04439","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.04439","created_at":"2026-07-05T09:17:45Z"},{"alias_kind":"arxiv_version","alias_value":"2407.04439v2","created_at":"2026-07-05T09:17:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.04439","created_at":"2026-07-05T09:17:45Z"},{"alias_kind":"pith_short_12","alias_value":"2KNTVW2SZFEN","created_at":"2026-07-05T09:17:45Z"},{"alias_kind":"pith_short_16","alias_value":"2KNTVW2SZFENQIKC","created_at":"2026-07-05T09:17:45Z"},{"alias_kind":"pith_short_8","alias_value":"2KNTVW2S","created_at":"2026-07-05T09:17:45Z"}],"graph_snapshots":[{"event_id":"sha256:b24645c19686921c13394283d64c611b6dbf25b2d3d07a9424c0e320168a7e77","target":"graph","created_at":"2026-07-05T09:17:45Z","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/2407.04439/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Self-supervised pretrained models exhibit competitive performance in automatic speech recognition on finetuning, even with limited in-domain supervised data. However, popular pretrained models are not suitable for streaming ASR because they are trained with full attention context. In this paper, we introduce XLSR-Transducer, where the XLSR-53 model is used as encoder in transducer setup. Our experiments on the AMI dataset reveal that the XLSR-Transducer achieves 4% absolute WER improvement over Whisper large-v2 and 8% over a Zipformer transducer model trained from scratch. To enable streaming ","authors_text":"Aravind Ganapathiraju, Esa\\'u Villatoro-Tello, Iuliia Thorbecke, Juan Zuluaga-Gomez, Manjunath K E, Petr Motlicek, Shashi Kumar, Srikanth Madikeri","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-07-05T11:41:11Z","title":"XLSR-Transducer: Streaming ASR for Self-Supervised Pretrained Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.04439","kind":"arxiv","version":2},"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":"sha256:9cf2b02ad6df569997246eac582e36d43f436517963ea3cd0cd6e1ff10382433","target":"record","created_at":"2026-07-05T09:17:45Z","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":"661fab7655017d72c6c423aaec510b1939cb475480a01a220dbc90bd8300e630","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-07-05T11:41:11Z","title_canon_sha256":"e7004d6f3d7e712dd16c005b5504f093ed600d97994f15fff437cb6bee2f8169"},"schema_version":"1.0","source":{"id":"2407.04439","kind":"arxiv","version":2}},"canonical_sha256":"d29b3adb52c948d82142fb83bfd4e564ba43079431e9db325e364c35ba7e432f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d29b3adb52c948d82142fb83bfd4e564ba43079431e9db325e364c35ba7e432f","first_computed_at":"2026-07-05T09:17:45.178095Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:17:45.178095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+eRWNgWvKlxPA1qcuginAzKCOtEEiQVPSadPWlB2RRV5R8ZKGe06md57+7SCcVRdeaNs5wypBKN5cYfy5YmOBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:17:45.178573Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.04439","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9cf2b02ad6df569997246eac582e36d43f436517963ea3cd0cd6e1ff10382433","sha256:b24645c19686921c13394283d64c611b6dbf25b2d3d07a9424c0e320168a7e77"],"state_sha256":"2eb013742b7e0e0f8f575164b53c51b0344635139842b709dab736f460aedfde"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FpQZZMlQssusZA5Ia/qBMJzvBkbG8K09M3/zr9K9I2esQamwUuIyMFfE6uxNwQcg8xgS/Ylv0gaj2vT8tFl0Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T09:40:01.262830Z","bundle_sha256":"226c4ad1f419c01a8f40250b4464e4fa6f0228d71249a489b202a93d5497e3e4"}}