{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:L2POJS5BA6XH7XRW4CYWNTNPCO","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":"9c167dfb44f8e5a4bb76afb7acee0a1d161df5b6225ceb8b997f7be3fdd40599","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-31T23:01:50Z","title_canon_sha256":"f3097680ae65bd218bbcfbc3ce5f69c3b43828289566fd8babd972818f7b2298"},"schema_version":"1.0","source":{"id":"2506.00740","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00740","created_at":"2026-07-05T11:13:39Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00740v1","created_at":"2026-07-05T11:13:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00740","created_at":"2026-07-05T11:13:39Z"},{"alias_kind":"pith_short_12","alias_value":"L2POJS5BA6XH","created_at":"2026-07-05T11:13:39Z"},{"alias_kind":"pith_short_16","alias_value":"L2POJS5BA6XH7XRW","created_at":"2026-07-05T11:13:39Z"},{"alias_kind":"pith_short_8","alias_value":"L2POJS5B","created_at":"2026-07-05T11:13:39Z"}],"graph_snapshots":[{"event_id":"sha256:6da3f1c5e0b60ad6b331ede826c87d09e97e1d742ae2145a3c0f243c78548ec3","target":"graph","created_at":"2026-07-05T11:13:39Z","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/2506.00740/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In video dubbing, aligning translated audio with the source audio is a significant challenge. Our focus is on achieving this efficiently, tailored for real-time, on-device video dubbing scenarios. We developed a phoneme-based end-to-end length-sensitive speech translation (LSST) model, which generates translations of varying lengths short, normal, and long using predefined tags. Additionally, we introduced length-aware beam search (LABS), an efficient approach to generate translations of different lengths in a single decoding pass. This approach maintained comparable BLEU scores compared to a ","authors_text":"Aswin Shanmugam Subramanian, Harveen Singh Chadha, Jian Xue, Jinyu Li, Rupeshkumar Mehta, Shubham Bansal, Vikas Joshi","cross_cats":["cs.AI","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-31T23:01:50Z","title":"Length Aware Speech Translation for Video Dubbing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00740","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":"sha256:832febea5e059e5e895612ee5683587469c63cb743a4fb76c95a65af44811631","target":"record","created_at":"2026-07-05T11:13:39Z","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":"9c167dfb44f8e5a4bb76afb7acee0a1d161df5b6225ceb8b997f7be3fdd40599","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-31T23:01:50Z","title_canon_sha256":"f3097680ae65bd218bbcfbc3ce5f69c3b43828289566fd8babd972818f7b2298"},"schema_version":"1.0","source":{"id":"2506.00740","kind":"arxiv","version":1}},"canonical_sha256":"5e9ee4cba107ae7fde36e0b166cdaf13abbc42522fd261d18e6cb126151cac44","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5e9ee4cba107ae7fde36e0b166cdaf13abbc42522fd261d18e6cb126151cac44","first_computed_at":"2026-07-05T11:13:39.716503Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:39.716503Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Eac2pvmN8Z54DYi3lmRvKAEJz6Z5ZcKzJPvLeRbSKXIHMcdRxi8KoIqoKv+oK1m2xpGFrOjfyHC5wcHtgLTnDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:39.716992Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.00740","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:832febea5e059e5e895612ee5683587469c63cb743a4fb76c95a65af44811631","sha256:6da3f1c5e0b60ad6b331ede826c87d09e97e1d742ae2145a3c0f243c78548ec3"],"state_sha256":"5c52d61b80f6212da2a0302657b234c7144bdfc1a70bdf95e9d4668913b7a5ac"}