{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:JBHR7GWGU57WL4BDQB4ES6GEVG","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":"76a9a1a2bbd27f496aef6905aa91d55a51c0bc372e4ccc5a304af5add9d0dc00","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-07-07T08:13:40Z","title_canon_sha256":"3ede4219ac93917ed84ef126d673fdae88e5ba692baf73dbd0a2974fd870d5a5"},"schema_version":"1.0","source":{"id":"2107.03069","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.03069","created_at":"2026-07-05T02:56:00Z"},{"alias_kind":"arxiv_version","alias_value":"2107.03069v1","created_at":"2026-07-05T02:56:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.03069","created_at":"2026-07-05T02:56:00Z"},{"alias_kind":"pith_short_12","alias_value":"JBHR7GWGU57W","created_at":"2026-07-05T02:56:00Z"},{"alias_kind":"pith_short_16","alias_value":"JBHR7GWGU57WL4BD","created_at":"2026-07-05T02:56:00Z"},{"alias_kind":"pith_short_8","alias_value":"JBHR7GWG","created_at":"2026-07-05T02:56:00Z"}],"graph_snapshots":[{"event_id":"sha256:51ab551a577a120d3288984d759cb1fdfd608ae9d88094de664c56160e60ff36","target":"graph","created_at":"2026-07-05T02:56:00Z","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/2107.03069/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The advent of Transformer-based models has surpassed the barriers of text. When working with speech, we must face a problem: the sequence length of an audio input is not suitable for the Transformer. To bypass this problem, a usual approach is adding strided convolutional layers, to reduce the sequence length before using the Transformer. In this paper, we propose a new approach for direct Speech Translation, where thanks to an efficient Transformer we can work with a spectrogram without having to use convolutional layers before the Transformer. This allows the encoder to learn directly from t","authors_text":"Belen Alastruey, Gerard I. G\\'allego, Marta R. Costa-juss\\`a","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-07-07T08:13:40Z","title":"Efficient Transformer for Direct Speech Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.03069","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":"sha256:434ee92a00a4eb49d9324348d645036c5a78374c58f8ae52a1ae9d9fe9ec1fc7","target":"record","created_at":"2026-07-05T02:56:00Z","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":"76a9a1a2bbd27f496aef6905aa91d55a51c0bc372e4ccc5a304af5add9d0dc00","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-07-07T08:13:40Z","title_canon_sha256":"3ede4219ac93917ed84ef126d673fdae88e5ba692baf73dbd0a2974fd870d5a5"},"schema_version":"1.0","source":{"id":"2107.03069","kind":"arxiv","version":1}},"canonical_sha256":"484f1f9ac6a77f65f02380784978c4a995c280b93743692a0a89c3a51333793d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"484f1f9ac6a77f65f02380784978c4a995c280b93743692a0a89c3a51333793d","first_computed_at":"2026-07-05T02:56:00.256014Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:56:00.256014Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CDz2cBu1DErYOifIV+X10wIdNBLGiHXHJNSgoRFpKmsaK4+/2IoVbkxv5qXEIUvs1NAmybLF/h7TklV1AEmqBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:56:00.256567Z","signed_message":"canonical_sha256_bytes"},"source_id":"2107.03069","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:434ee92a00a4eb49d9324348d645036c5a78374c58f8ae52a1ae9d9fe9ec1fc7","sha256:51ab551a577a120d3288984d759cb1fdfd608ae9d88094de664c56160e60ff36"],"state_sha256":"e17ae90631a838b3610aa5929a44eaa9ff97670b61156f940e9cc09813a0d2d3"}