{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:E2ZM3OXITXC2SS76NKKHZUVMUW","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":"452848a836dfe16b6e97350f7f38bd13c13ebe03f4bb1195b9556ea679763594","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-09T06:35:46Z","title_canon_sha256":"403a094b27aa171ebc690e04bc8763488efaf88590bea203a326444109746c3e"},"schema_version":"1.0","source":{"id":"2106.04833","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.04833","created_at":"2026-07-05T02:47:49Z"},{"alias_kind":"arxiv_version","alias_value":"2106.04833v1","created_at":"2026-07-05T02:47:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.04833","created_at":"2026-07-05T02:47:49Z"},{"alias_kind":"pith_short_12","alias_value":"E2ZM3OXITXC2","created_at":"2026-07-05T02:47:49Z"},{"alias_kind":"pith_short_16","alias_value":"E2ZM3OXITXC2SS76","created_at":"2026-07-05T02:47:49Z"},{"alias_kind":"pith_short_8","alias_value":"E2ZM3OXI","created_at":"2026-07-05T02:47:49Z"}],"graph_snapshots":[{"event_id":"sha256:8045f98d6e0ae2f46f9a17d7b67f234ea3293d363c0b7d0208500842b10389c1","target":"graph","created_at":"2026-07-05T02:47:49Z","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/2106.04833/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"End-to-end simultaneous speech translation (SST), which directly translates speech in one language into text in another language in real-time, is useful in many scenarios but has not been fully investigated. In this work, we propose RealTranS, an end-to-end model for SST. To bridge the modality gap between speech and text, RealTranS gradually downsamples the input speech with interleaved convolution and unidirectional Transformer layers for acoustic modeling, and then maps speech features into text space with a weighted-shrinking operation and a semantic encoder. Besides, to improve the model ","authors_text":"Liangyou Li, Qun Liu, Xingshan Zeng","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-09T06:35:46Z","title":"RealTranS: End-to-End Simultaneous Speech Translation with Convolutional Weighted-Shrinking Transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.04833","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":"sha256:5433a5a8bcbb382a5a51b84bae2422713943d348cf75c8dab87b4b2bcfb871ba","target":"record","created_at":"2026-07-05T02:47:49Z","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":"452848a836dfe16b6e97350f7f38bd13c13ebe03f4bb1195b9556ea679763594","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-09T06:35:46Z","title_canon_sha256":"403a094b27aa171ebc690e04bc8763488efaf88590bea203a326444109746c3e"},"schema_version":"1.0","source":{"id":"2106.04833","kind":"arxiv","version":1}},"canonical_sha256":"26b2cdbae89dc5a94bfe6a947cd2aca58293089f9e2dde93a8e4ec26fb48104d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"26b2cdbae89dc5a94bfe6a947cd2aca58293089f9e2dde93a8e4ec26fb48104d","first_computed_at":"2026-07-05T02:47:49.556577Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:47:49.556577Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HtQaLRup3UGQu9/mGxY7QlXdSDHMWBnuPFh37S96OOcs4VvVehrXCO9ZN7V2gmd9xW11RAqsJaady5MADUvdBg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:47:49.557090Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.04833","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5433a5a8bcbb382a5a51b84bae2422713943d348cf75c8dab87b4b2bcfb871ba","sha256:8045f98d6e0ae2f46f9a17d7b67f234ea3293d363c0b7d0208500842b10389c1"],"state_sha256":"68882faf05e84b4dba75d101e7c738ebd368c8ae598510221d6c195aa041ca8e"}