{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:QJ6GJ3WJNHQIQ55E4HVCNJ3LS5","short_pith_number":"pith:QJ6GJ3WJ","canonical_record":{"source":{"id":"2412.15415","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-12-19T21:57:01Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"e774145a286a83bdce9d993bbf3529fc832955587f1edd253c624c967fb4f008","abstract_canon_sha256":"c924314d1bc6022d13b3661da909c9bac2e267f488acbd3021c98de5d6effc99"},"schema_version":"1.0"},"canonical_sha256":"827c64eec969e08877a4e1ea26a76b975cb5aadf36019454bb3d1e8ee5f1d46a","source":{"kind":"arxiv","id":"2412.15415","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.15415","created_at":"2026-07-05T09:52:22Z"},{"alias_kind":"arxiv_version","alias_value":"2412.15415v1","created_at":"2026-07-05T09:52:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.15415","created_at":"2026-07-05T09:52:22Z"},{"alias_kind":"pith_short_12","alias_value":"QJ6GJ3WJNHQI","created_at":"2026-07-05T09:52:22Z"},{"alias_kind":"pith_short_16","alias_value":"QJ6GJ3WJNHQIQ55E","created_at":"2026-07-05T09:52:22Z"},{"alias_kind":"pith_short_8","alias_value":"QJ6GJ3WJ","created_at":"2026-07-05T09:52:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:QJ6GJ3WJNHQIQ55E4HVCNJ3LS5","target":"record","payload":{"canonical_record":{"source":{"id":"2412.15415","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-12-19T21:57:01Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"e774145a286a83bdce9d993bbf3529fc832955587f1edd253c624c967fb4f008","abstract_canon_sha256":"c924314d1bc6022d13b3661da909c9bac2e267f488acbd3021c98de5d6effc99"},"schema_version":"1.0"},"canonical_sha256":"827c64eec969e08877a4e1ea26a76b975cb5aadf36019454bb3d1e8ee5f1d46a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:52:22.945474Z","signature_b64":"Anoov97MP2+44NUDjfYZz84+qZ3PYbI2jeU1s5asjErmRJIytiQozdhH9yaWJM8Ya09kBBO0C+kSTLzcjfkxDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"827c64eec969e08877a4e1ea26a76b975cb5aadf36019454bb3d1e8ee5f1d46a","last_reissued_at":"2026-07-05T09:52:22.944978Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:52:22.944978Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.15415","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":"2026-07-05T09:52:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AFMcBi4bdvs4TagVnbVfmXLE1DD/aaAX8vJJAWX5Bm5qMp0iH0ZaNPOSdLzmycTPZ+Sj1aKJkdondXSNXkTcDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T09:42:51.848204Z"},"content_sha256":"565cc2b48baf58e56d0dd89889e00feb6d03114ab1f65f7b273b6b7a06900f48","schema_version":"1.0","event_id":"sha256:565cc2b48baf58e56d0dd89889e00feb6d03114ab1f65f7b273b6b7a06900f48"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:QJ6GJ3WJNHQIQ55E4HVCNJ3LS5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Transcribing and Translating, Fast and Slow: Joint Speech Translation and Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"eess.AS","authors_text":"Christian Fuegen, Frank Seide, Ke Li, Niko Moritz, Ruiming Xie, Simone Merello, Yashesh Gaur, Zeeshan Ahmed","submitted_at":"2024-12-19T21:57:01Z","abstract_excerpt":"We propose the joint speech translation and recognition (JSTAR) model that leverages the fast-slow cascaded encoder architecture for simultaneous end-to-end automatic speech recognition (ASR) and speech translation (ST). The model is transducer-based and uses a multi-objective training strategy that optimizes both ASR and ST objectives simultaneously. This allows JSTAR to produce high-quality streaming ASR and ST results. We apply JSTAR in a bilingual conversational speech setting with smart-glasses, where the model is also trained to distinguish speech from different directions corresponding "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.15415","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/2412.15415/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":"2026-07-05T09:52:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WjCRLvR/kS652UxibUOfhX4Fbqx4MGILNDI9/+NYVMjRKjtJY97DCws8Jd6moE/1qK6+KV3KK4N7yn3ymLyVBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T09:42:51.848586Z"},"content_sha256":"4ce196fad05060d5c464cdeff7a9ad4ce91136c8bb05e4293af11e60dafb2637","schema_version":"1.0","event_id":"sha256:4ce196fad05060d5c464cdeff7a9ad4ce91136c8bb05e4293af11e60dafb2637"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QJ6GJ3WJNHQIQ55E4HVCNJ3LS5/bundle.json","state_url":"https://pith.science/pith/QJ6GJ3WJNHQIQ55E4HVCNJ3LS5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QJ6GJ3WJNHQIQ55E4HVCNJ3LS5/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":"2026-07-17T09:42:51Z","links":{"resolver":"https://pith.science/pith/QJ6GJ3WJNHQIQ55E4HVCNJ3LS5","bundle":"https://pith.science/pith/QJ6GJ3WJNHQIQ55E4HVCNJ3LS5/bundle.json","state":"https://pith.science/pith/QJ6GJ3WJNHQIQ55E4HVCNJ3LS5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QJ6GJ3WJNHQIQ55E4HVCNJ3LS5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QJ6GJ3WJNHQIQ55E4HVCNJ3LS5","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":"c924314d1bc6022d13b3661da909c9bac2e267f488acbd3021c98de5d6effc99","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-12-19T21:57:01Z","title_canon_sha256":"e774145a286a83bdce9d993bbf3529fc832955587f1edd253c624c967fb4f008"},"schema_version":"1.0","source":{"id":"2412.15415","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.15415","created_at":"2026-07-05T09:52:22Z"},{"alias_kind":"arxiv_version","alias_value":"2412.15415v1","created_at":"2026-07-05T09:52:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.15415","created_at":"2026-07-05T09:52:22Z"},{"alias_kind":"pith_short_12","alias_value":"QJ6GJ3WJNHQI","created_at":"2026-07-05T09:52:22Z"},{"alias_kind":"pith_short_16","alias_value":"QJ6GJ3WJNHQIQ55E","created_at":"2026-07-05T09:52:22Z"},{"alias_kind":"pith_short_8","alias_value":"QJ6GJ3WJ","created_at":"2026-07-05T09:52:22Z"}],"graph_snapshots":[{"event_id":"sha256:4ce196fad05060d5c464cdeff7a9ad4ce91136c8bb05e4293af11e60dafb2637","target":"graph","created_at":"2026-07-05T09:52:22Z","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/2412.15415/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose the joint speech translation and recognition (JSTAR) model that leverages the fast-slow cascaded encoder architecture for simultaneous end-to-end automatic speech recognition (ASR) and speech translation (ST). The model is transducer-based and uses a multi-objective training strategy that optimizes both ASR and ST objectives simultaneously. This allows JSTAR to produce high-quality streaming ASR and ST results. We apply JSTAR in a bilingual conversational speech setting with smart-glasses, where the model is also trained to distinguish speech from different directions corresponding ","authors_text":"Christian Fuegen, Frank Seide, Ke Li, Niko Moritz, Ruiming Xie, Simone Merello, Yashesh Gaur, Zeeshan Ahmed","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-12-19T21:57:01Z","title":"Transcribing and Translating, Fast and Slow: Joint Speech Translation and Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.15415","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":"sha256:565cc2b48baf58e56d0dd89889e00feb6d03114ab1f65f7b273b6b7a06900f48","target":"record","created_at":"2026-07-05T09:52:22Z","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":"c924314d1bc6022d13b3661da909c9bac2e267f488acbd3021c98de5d6effc99","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-12-19T21:57:01Z","title_canon_sha256":"e774145a286a83bdce9d993bbf3529fc832955587f1edd253c624c967fb4f008"},"schema_version":"1.0","source":{"id":"2412.15415","kind":"arxiv","version":1}},"canonical_sha256":"827c64eec969e08877a4e1ea26a76b975cb5aadf36019454bb3d1e8ee5f1d46a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"827c64eec969e08877a4e1ea26a76b975cb5aadf36019454bb3d1e8ee5f1d46a","first_computed_at":"2026-07-05T09:52:22.944978Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:52:22.944978Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Anoov97MP2+44NUDjfYZz84+qZ3PYbI2jeU1s5asjErmRJIytiQozdhH9yaWJM8Ya09kBBO0C+kSTLzcjfkxDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:52:22.945474Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.15415","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:565cc2b48baf58e56d0dd89889e00feb6d03114ab1f65f7b273b6b7a06900f48","sha256:4ce196fad05060d5c464cdeff7a9ad4ce91136c8bb05e4293af11e60dafb2637"],"state_sha256":"286f79f454c462f429217b38a06ec952f7d06c91e48b35eda1fd580f1c95306c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"38oviEOc9KV0mH9efvWifihxOp5lYj/9C7YlsN4rheO3ugjW0wVugR8MixuFAW3JfomGKcKltN/N/6PTmwdNAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-17T09:42:51.851124Z","bundle_sha256":"0b1cf3692ceccc972f899eac4f9e44d4771c4a5c251e504ce7a8192b1e2ce00b"}}