{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:OJIDZ7LP53KAHI57WDG2FNXXA5","short_pith_number":"pith:OJIDZ7LP","canonical_record":{"source":{"id":"2409.13523","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-20T14:03:23Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"06cbabc822f3865cf136723b5f23301eadb56ab1196682ed0fac6580b99259fb","abstract_canon_sha256":"ea1b4f92b4a76ceb664c602c31f5fa7e0ce015a9a4c3be050cec2cb07f26b04b"},"schema_version":"1.0"},"canonical_sha256":"72503cfd6feed403a3bfb0cda2b6f7077c32e47389bf890708c84f5c130e7207","source":{"kind":"arxiv","id":"2409.13523","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.13523","created_at":"2026-07-05T09:09:37Z"},{"alias_kind":"arxiv_version","alias_value":"2409.13523v1","created_at":"2026-07-05T09:09:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.13523","created_at":"2026-07-05T09:09:37Z"},{"alias_kind":"pith_short_12","alias_value":"OJIDZ7LP53KA","created_at":"2026-07-05T09:09:37Z"},{"alias_kind":"pith_short_16","alias_value":"OJIDZ7LP53KAHI57","created_at":"2026-07-05T09:09:37Z"},{"alias_kind":"pith_short_8","alias_value":"OJIDZ7LP","created_at":"2026-07-05T09:09:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:OJIDZ7LP53KAHI57WDG2FNXXA5","target":"record","payload":{"canonical_record":{"source":{"id":"2409.13523","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-20T14:03:23Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"06cbabc822f3865cf136723b5f23301eadb56ab1196682ed0fac6580b99259fb","abstract_canon_sha256":"ea1b4f92b4a76ceb664c602c31f5fa7e0ce015a9a4c3be050cec2cb07f26b04b"},"schema_version":"1.0"},"canonical_sha256":"72503cfd6feed403a3bfb0cda2b6f7077c32e47389bf890708c84f5c130e7207","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:09:37.009447Z","signature_b64":"44+MJd5M1piY8geUx+vLYf0htWPJ9cU4mlNtdgvuMyqgFJ11truVwVcqaPoTxbJEBP5U861v4fq8/43tdPTPBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"72503cfd6feed403a3bfb0cda2b6f7077c32e47389bf890708c84f5c130e7207","last_reissued_at":"2026-07-05T09:09:37.008983Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:09:37.008983Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.13523","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":"2026-07-05T09:09:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"czof2Ku5lFfh87+PuqqEk0UMy0hftwzDXuTNkaH7ibM2dfxXqHaIoibJD/MbQrNh6cdljDav1rfQ2p1PPP8+Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:45:38.804377Z"},"content_sha256":"99f7265e1bafa3297afd47521c5c5b8b1f1666e4bbf1da959d147b9d11926878","schema_version":"1.0","event_id":"sha256:99f7265e1bafa3297afd47521c5c5b8b1f1666e4bbf1da959d147b9d11926878"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:OJIDZ7LP53KAHI57WDG2FNXXA5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"EMMeTT: Efficient Multimodal Machine Translation Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Boris Ginsburg, Daniel Galvez, Jagadeesh Balam, Ke Hu, Mengru Wang, Oleksii Hrinchuk, Piotr \\.Zelasko, Shuoyang Ding, Vitaly Lavrukhin, Zhehuai Chen","submitted_at":"2024-09-20T14:03:23Z","abstract_excerpt":"A rising interest in the modality extension of foundation language models warrants discussion on the most effective, and efficient, multimodal training approach. This work focuses on neural machine translation (NMT) and proposes a joint multimodal training regime of Speech-LLM to include automatic speech translation (AST). We investigate two different foundation model architectures, decoder-only GPT and encoder-decoder T5, extended with Canary-1B's speech encoder. To handle joint multimodal training, we propose a novel training framework called EMMeTT. EMMeTT improves training efficiency with "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.13523","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/2409.13523/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":"2026-07-05T09:09:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7/p3pBQLG9gmfjyoL8GASJ/kJFlIHrcTTmQyivNf9DzYZvOdYm2WXvTXU5ivOq2IAIlfN4kIFul5WdmArkBdDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:45:38.804756Z"},"content_sha256":"49aa28a8740ed8e3b4cadaf1cba6a71bcf5fde6a8479495f8a9eb5b7c5bb03af","schema_version":"1.0","event_id":"sha256:49aa28a8740ed8e3b4cadaf1cba6a71bcf5fde6a8479495f8a9eb5b7c5bb03af"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OJIDZ7LP53KAHI57WDG2FNXXA5/bundle.json","state_url":"https://pith.science/pith/OJIDZ7LP53KAHI57WDG2FNXXA5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OJIDZ7LP53KAHI57WDG2FNXXA5/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":"2026-07-06T18:45:38Z","links":{"resolver":"https://pith.science/pith/OJIDZ7LP53KAHI57WDG2FNXXA5","bundle":"https://pith.science/pith/OJIDZ7LP53KAHI57WDG2FNXXA5/bundle.json","state":"https://pith.science/pith/OJIDZ7LP53KAHI57WDG2FNXXA5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OJIDZ7LP53KAHI57WDG2FNXXA5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OJIDZ7LP53KAHI57WDG2FNXXA5","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":"ea1b4f92b4a76ceb664c602c31f5fa7e0ce015a9a4c3be050cec2cb07f26b04b","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-20T14:03:23Z","title_canon_sha256":"06cbabc822f3865cf136723b5f23301eadb56ab1196682ed0fac6580b99259fb"},"schema_version":"1.0","source":{"id":"2409.13523","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.13523","created_at":"2026-07-05T09:09:37Z"},{"alias_kind":"arxiv_version","alias_value":"2409.13523v1","created_at":"2026-07-05T09:09:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.13523","created_at":"2026-07-05T09:09:37Z"},{"alias_kind":"pith_short_12","alias_value":"OJIDZ7LP53KA","created_at":"2026-07-05T09:09:37Z"},{"alias_kind":"pith_short_16","alias_value":"OJIDZ7LP53KAHI57","created_at":"2026-07-05T09:09:37Z"},{"alias_kind":"pith_short_8","alias_value":"OJIDZ7LP","created_at":"2026-07-05T09:09:37Z"}],"graph_snapshots":[{"event_id":"sha256:49aa28a8740ed8e3b4cadaf1cba6a71bcf5fde6a8479495f8a9eb5b7c5bb03af","target":"graph","created_at":"2026-07-05T09:09:37Z","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/2409.13523/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A rising interest in the modality extension of foundation language models warrants discussion on the most effective, and efficient, multimodal training approach. This work focuses on neural machine translation (NMT) and proposes a joint multimodal training regime of Speech-LLM to include automatic speech translation (AST). We investigate two different foundation model architectures, decoder-only GPT and encoder-decoder T5, extended with Canary-1B's speech encoder. To handle joint multimodal training, we propose a novel training framework called EMMeTT. EMMeTT improves training efficiency with ","authors_text":"Boris Ginsburg, Daniel Galvez, Jagadeesh Balam, Ke Hu, Mengru Wang, Oleksii Hrinchuk, Piotr \\.Zelasko, Shuoyang Ding, Vitaly Lavrukhin, Zhehuai Chen","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-20T14:03:23Z","title":"EMMeTT: Efficient Multimodal Machine Translation Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.13523","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":"sha256:99f7265e1bafa3297afd47521c5c5b8b1f1666e4bbf1da959d147b9d11926878","target":"record","created_at":"2026-07-05T09:09:37Z","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":"ea1b4f92b4a76ceb664c602c31f5fa7e0ce015a9a4c3be050cec2cb07f26b04b","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-20T14:03:23Z","title_canon_sha256":"06cbabc822f3865cf136723b5f23301eadb56ab1196682ed0fac6580b99259fb"},"schema_version":"1.0","source":{"id":"2409.13523","kind":"arxiv","version":1}},"canonical_sha256":"72503cfd6feed403a3bfb0cda2b6f7077c32e47389bf890708c84f5c130e7207","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"72503cfd6feed403a3bfb0cda2b6f7077c32e47389bf890708c84f5c130e7207","first_computed_at":"2026-07-05T09:09:37.008983Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:09:37.008983Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"44+MJd5M1piY8geUx+vLYf0htWPJ9cU4mlNtdgvuMyqgFJ11truVwVcqaPoTxbJEBP5U861v4fq8/43tdPTPBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:09:37.009447Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.13523","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:99f7265e1bafa3297afd47521c5c5b8b1f1666e4bbf1da959d147b9d11926878","sha256:49aa28a8740ed8e3b4cadaf1cba6a71bcf5fde6a8479495f8a9eb5b7c5bb03af"],"state_sha256":"93befedb420ec75fcf9dfb7b6c901147bd127e0dd46a186b6896172e4b31714d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1LIzfZgo1CtfcruhfEQ0hgSPtd2z+65Gr/gWOwHa94212JSWhLfYoohX71vuNjWxXKxTH9HBecZQNzuCUdgBCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T18:45:38.808019Z","bundle_sha256":"91eb286264486023aa85c198558ac0af610d04a36fe01cd7c49c075adee4565a"}}