{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:GH7GLHDHRNQCUVGYJQPWGV2SGP","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":"34cf53fee8210ff5ed0458ddbe15e7442f1052698e113caaae6ad7088ebd8318","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-01-27T14:03:09Z","title_canon_sha256":"2f00a6f317cba6576a90c2891c1a3842b3c977d565dce3d081f0491170497fff"},"schema_version":"1.0","source":{"id":"2301.11716","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.11716","created_at":"2026-07-05T06:17:27Z"},{"alias_kind":"arxiv_version","alias_value":"2301.11716v3","created_at":"2026-07-05T06:17:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.11716","created_at":"2026-07-05T06:17:27Z"},{"alias_kind":"pith_short_12","alias_value":"GH7GLHDHRNQC","created_at":"2026-07-05T06:17:27Z"},{"alias_kind":"pith_short_16","alias_value":"GH7GLHDHRNQCUVGY","created_at":"2026-07-05T06:17:27Z"},{"alias_kind":"pith_short_8","alias_value":"GH7GLHDH","created_at":"2026-07-05T06:17:27Z"}],"graph_snapshots":[{"event_id":"sha256:83e3e87f54046bbf24cedc531130c333e3c244707d3b1219a49a2b6aae35e932","target":"graph","created_at":"2026-07-05T06:17:27Z","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/2301.11716/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The gap between speech and text modalities is a major challenge in speech-to-text translation (ST). Different methods have been proposed to reduce this gap, but most of them require architectural changes in ST training. In this work, we propose to mitigate this issue at the pre-training stage, requiring no change in the ST model. First, we show that the connectionist temporal classification (CTC) loss can reduce the modality gap by design. We provide a quantitative comparison with the more common cross-entropy loss, showing that pre-training with CTC consistently achieves better final ST accur","authors_text":"Benjamin Lecouteux, Changhan Wang, Didier Schwab, Hongyu Gong, Juan Pino, Phuong-Hang Le","cross_cats":["cs.LG","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-01-27T14:03:09Z","title":"Pre-training for Speech Translation: CTC Meets Optimal Transport"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.11716","kind":"arxiv","version":3},"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":"sha256:05583dad0053b92dc822130f94f840469b4f18e4626b6421282939f56bf28363","target":"record","created_at":"2026-07-05T06:17:27Z","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":"34cf53fee8210ff5ed0458ddbe15e7442f1052698e113caaae6ad7088ebd8318","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-01-27T14:03:09Z","title_canon_sha256":"2f00a6f317cba6576a90c2891c1a3842b3c977d565dce3d081f0491170497fff"},"schema_version":"1.0","source":{"id":"2301.11716","kind":"arxiv","version":3}},"canonical_sha256":"31fe659c678b602a54d84c1f63575233f1db2cc01e161ac8b84c47dbbf3126cf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"31fe659c678b602a54d84c1f63575233f1db2cc01e161ac8b84c47dbbf3126cf","first_computed_at":"2026-07-05T06:17:27.548390Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:17:27.548390Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3pfPI7baAuLTtMNz60bTpp+zOpbcliSw2idkTQsi7b8DBwqvrXvZohe0tRCU/WG4w+AMpCOFhi6yj/X8/CmEDA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:17:27.548917Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.11716","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:05583dad0053b92dc822130f94f840469b4f18e4626b6421282939f56bf28363","sha256:83e3e87f54046bbf24cedc531130c333e3c244707d3b1219a49a2b6aae35e932"],"state_sha256":"7b07d41cbc773b727dbb34537df29073f55651097942c5242d3ed9db4be081f4"}