{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:YIVCVHTHYC2OJJHJ34XYINS4LT","short_pith_number":"pith:YIVCVHTH","canonical_record":{"source":{"id":"2305.14635","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T02:13:48Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"b8c8b6c7b11d9d4bea729c4e154c3da19437b51794b93a4be6942bdbe273c23f","abstract_canon_sha256":"b0d884c1c0e3d232d4f88a913a03a7629f5c7e83ae5e34074869c24cc38322fd"},"schema_version":"1.0"},"canonical_sha256":"c22a2a9e67c0b4e4a4e9df2f84365c5cd9be512c3fcf9332a4acd528997d8364","source":{"kind":"arxiv","id":"2305.14635","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.14635","created_at":"2026-07-05T06:13:40Z"},{"alias_kind":"arxiv_version","alias_value":"2305.14635v2","created_at":"2026-07-05T06:13:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14635","created_at":"2026-07-05T06:13:40Z"},{"alias_kind":"pith_short_12","alias_value":"YIVCVHTHYC2O","created_at":"2026-07-05T06:13:40Z"},{"alias_kind":"pith_short_16","alias_value":"YIVCVHTHYC2OJJHJ","created_at":"2026-07-05T06:13:40Z"},{"alias_kind":"pith_short_8","alias_value":"YIVCVHTH","created_at":"2026-07-05T06:13:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:YIVCVHTHYC2OJJHJ34XYINS4LT","target":"record","payload":{"canonical_record":{"source":{"id":"2305.14635","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T02:13:48Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"b8c8b6c7b11d9d4bea729c4e154c3da19437b51794b93a4be6942bdbe273c23f","abstract_canon_sha256":"b0d884c1c0e3d232d4f88a913a03a7629f5c7e83ae5e34074869c24cc38322fd"},"schema_version":"1.0"},"canonical_sha256":"c22a2a9e67c0b4e4a4e9df2f84365c5cd9be512c3fcf9332a4acd528997d8364","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:13:40.144002Z","signature_b64":"FPksCMJW5tSgsROrNxYFcQ9bGJ8A6kEXwVBudmqd2j1VuP+b9E4CsQQwjbzBHKmPhIsbe773nL4Q2lTYg59hAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c22a2a9e67c0b4e4a4e9df2f84365c5cd9be512c3fcf9332a4acd528997d8364","last_reissued_at":"2026-07-05T06:13:40.143624Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:13:40.143624Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.14635","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":"2026-07-05T06:13:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QPz3TdI0gVu6ccmv6OUObD1cJ4w9y0ZN/tsDx23jISq6KzLa5S2Rt7refCaztO4s7SNa0NhknTVpjFzs3E52DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T18:29:21.243414Z"},"content_sha256":"a10c34c2d12dd9eb8e6cec989b0713ffd5c5f0bc030d60592981b80670ad051f","schema_version":"1.0","event_id":"sha256:a10c34c2d12dd9eb8e6cec989b0713ffd5c5f0bc030d60592981b80670ad051f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:YIVCVHTHYC2OJJHJ34XYINS4LT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CMOT: Cross-modal Mixup via Optimal Transport for Speech Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Qingkai Fang, Yang Feng, Yan Zhou","submitted_at":"2023-05-24T02:13:48Z","abstract_excerpt":"End-to-end speech translation (ST) is the task of translating speech signals in the source language into text in the target language. As a cross-modal task, end-to-end ST is difficult to train with limited data. Existing methods often try to transfer knowledge from machine translation (MT), but their performances are restricted by the modality gap between speech and text. In this paper, we propose Cross-modal Mixup via Optimal Transport CMOT to overcome the modality gap. We find the alignment between speech and text sequences via optimal transport and then mix up the sequences from different m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14635","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/2305.14635/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":"2026-07-05T06:13:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PkBzGFTHSKleZ4FChh32xqLaSBQaL1ZTL1xELELJdUCgKO4ETxWGhPs6C7TIwHf2NmLlejXtDLP4Wo8P4Vm3Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T18:29:21.244164Z"},"content_sha256":"bcddcad241a039282bef15c5d43ba67da4ad3f0b596ef4d6874242ff6443ba5b","schema_version":"1.0","event_id":"sha256:bcddcad241a039282bef15c5d43ba67da4ad3f0b596ef4d6874242ff6443ba5b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YIVCVHTHYC2OJJHJ34XYINS4LT/bundle.json","state_url":"https://pith.science/pith/YIVCVHTHYC2OJJHJ34XYINS4LT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YIVCVHTHYC2OJJHJ34XYINS4LT/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":"2026-08-17T18:29:21Z","links":{"resolver":"https://pith.science/pith/YIVCVHTHYC2OJJHJ34XYINS4LT","bundle":"https://pith.science/pith/YIVCVHTHYC2OJJHJ34XYINS4LT/bundle.json","state":"https://pith.science/pith/YIVCVHTHYC2OJJHJ34XYINS4LT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YIVCVHTHYC2OJJHJ34XYINS4LT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:YIVCVHTHYC2OJJHJ34XYINS4LT","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":"b0d884c1c0e3d232d4f88a913a03a7629f5c7e83ae5e34074869c24cc38322fd","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T02:13:48Z","title_canon_sha256":"b8c8b6c7b11d9d4bea729c4e154c3da19437b51794b93a4be6942bdbe273c23f"},"schema_version":"1.0","source":{"id":"2305.14635","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.14635","created_at":"2026-07-05T06:13:40Z"},{"alias_kind":"arxiv_version","alias_value":"2305.14635v2","created_at":"2026-07-05T06:13:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14635","created_at":"2026-07-05T06:13:40Z"},{"alias_kind":"pith_short_12","alias_value":"YIVCVHTHYC2O","created_at":"2026-07-05T06:13:40Z"},{"alias_kind":"pith_short_16","alias_value":"YIVCVHTHYC2OJJHJ","created_at":"2026-07-05T06:13:40Z"},{"alias_kind":"pith_short_8","alias_value":"YIVCVHTH","created_at":"2026-07-05T06:13:40Z"}],"graph_snapshots":[{"event_id":"sha256:bcddcad241a039282bef15c5d43ba67da4ad3f0b596ef4d6874242ff6443ba5b","target":"graph","created_at":"2026-07-05T06:13:40Z","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/2305.14635/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"End-to-end speech translation (ST) is the task of translating speech signals in the source language into text in the target language. As a cross-modal task, end-to-end ST is difficult to train with limited data. Existing methods often try to transfer knowledge from machine translation (MT), but their performances are restricted by the modality gap between speech and text. In this paper, we propose Cross-modal Mixup via Optimal Transport CMOT to overcome the modality gap. We find the alignment between speech and text sequences via optimal transport and then mix up the sequences from different m","authors_text":"Qingkai Fang, Yang Feng, Yan Zhou","cross_cats":["cs.AI","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T02:13:48Z","title":"CMOT: Cross-modal Mixup via Optimal Transport for Speech Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14635","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:a10c34c2d12dd9eb8e6cec989b0713ffd5c5f0bc030d60592981b80670ad051f","target":"record","created_at":"2026-07-05T06:13:40Z","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":"b0d884c1c0e3d232d4f88a913a03a7629f5c7e83ae5e34074869c24cc38322fd","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T02:13:48Z","title_canon_sha256":"b8c8b6c7b11d9d4bea729c4e154c3da19437b51794b93a4be6942bdbe273c23f"},"schema_version":"1.0","source":{"id":"2305.14635","kind":"arxiv","version":2}},"canonical_sha256":"c22a2a9e67c0b4e4a4e9df2f84365c5cd9be512c3fcf9332a4acd528997d8364","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c22a2a9e67c0b4e4a4e9df2f84365c5cd9be512c3fcf9332a4acd528997d8364","first_computed_at":"2026-07-05T06:13:40.143624Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:13:40.143624Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FPksCMJW5tSgsROrNxYFcQ9bGJ8A6kEXwVBudmqd2j1VuP+b9E4CsQQwjbzBHKmPhIsbe773nL4Q2lTYg59hAA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:13:40.144002Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.14635","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a10c34c2d12dd9eb8e6cec989b0713ffd5c5f0bc030d60592981b80670ad051f","sha256:bcddcad241a039282bef15c5d43ba67da4ad3f0b596ef4d6874242ff6443ba5b"],"state_sha256":"9ccbad2ac77569782f8efa483851f7e41567ad2248ac98499f2a73f45a3aadd6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XWWwFN1mTd9kyySTJe86DanqnHSLO+XWrlFyY6yrRIbBSbFv2jrEILi6ho2WO+HclcrA7ALHkDhamNk2nLjYAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T18:29:21.251916Z","bundle_sha256":"48f51b85b9cffb747ea22c4a009df1c6664eaa7527117b1ee68c70e929a81ea8"}}