{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:LOV344YSF2VGCACK3KGE2Y5XEJ","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":"ccd0b2ac10220ae212c2f0047d98f80fa99eca4f99a6e857065328d6c42c0ec3","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-19T10:49:35Z","title_canon_sha256":"430c0e4bee78523a1d7c4d22f7967d88127800ee1c235758f00e93549d1854fe"},"schema_version":"1.0","source":{"id":"2212.09359","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.09359","created_at":"2026-07-05T06:28:33Z"},{"alias_kind":"arxiv_version","alias_value":"2212.09359v3","created_at":"2026-07-05T06:28:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.09359","created_at":"2026-07-05T06:28:33Z"},{"alias_kind":"pith_short_12","alias_value":"LOV344YSF2VG","created_at":"2026-07-05T06:28:33Z"},{"alias_kind":"pith_short_16","alias_value":"LOV344YSF2VGCACK","created_at":"2026-07-05T06:28:33Z"},{"alias_kind":"pith_short_8","alias_value":"LOV344YS","created_at":"2026-07-05T06:28:33Z"}],"graph_snapshots":[{"event_id":"sha256:dd305887c6daff3c01b319ebc84e4c8ee5365009cfa383ec2574254a0de23bda","target":"graph","created_at":"2026-07-05T06:28:33Z","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/2212.09359/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"End-to-end Speech Translation (E2E ST) aims to directly translate source speech into target text. Existing ST methods perform poorly when only extremely small speech-text data are available for training. We observe that an ST model's performance closely correlates with its embedding similarity between speech and source transcript. In this paper, we propose Word-Aligned COntrastive learning (WACO), a simple and effective method for extremely low-resource speech-to-text translation. Our key idea is bridging word-level representations for both speech and text modalities via contrastive learning. ","authors_text":"Lei Li, Rong Ye, Siqi Ouyang","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-19T10:49:35Z","title":"WACO: Word-Aligned Contrastive Learning for Speech Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.09359","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":"sha256:774c94fa6d3fee71b398a623c0f0035aac83b90c5da51b112d2c6d67e5b558a7","target":"record","created_at":"2026-07-05T06:28:33Z","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":"ccd0b2ac10220ae212c2f0047d98f80fa99eca4f99a6e857065328d6c42c0ec3","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-19T10:49:35Z","title_canon_sha256":"430c0e4bee78523a1d7c4d22f7967d88127800ee1c235758f00e93549d1854fe"},"schema_version":"1.0","source":{"id":"2212.09359","kind":"arxiv","version":3}},"canonical_sha256":"5babbe73122eaa61004ada8c4d63b7227233143002f660465777ff79f4106f07","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5babbe73122eaa61004ada8c4d63b7227233143002f660465777ff79f4106f07","first_computed_at":"2026-07-05T06:28:33.166288Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:28:33.166288Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"o15NHTNoHrU667w8dUCG8Ws8ApBjF02sWKL/EhF7bAcDWmuWvwePXgy/TkZ2+nZYHX1Z6SejHjqwx6aDXQ6/Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:28:33.166793Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.09359","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:774c94fa6d3fee71b398a623c0f0035aac83b90c5da51b112d2c6d67e5b558a7","sha256:dd305887c6daff3c01b319ebc84e4c8ee5365009cfa383ec2574254a0de23bda"],"state_sha256":"71e30b5b37e4146cc0f1801095e947ffd589f2f0b82c11269ab87179009e9fdd"}