{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:Y4LUNSHIBRKRTE4QAJSIWSU2U2","short_pith_number":"pith:Y4LUNSHI","schema_version":"1.0","canonical_sha256":"c71746c8e80c5519939002648b4a9aa6a1f9df6c412cc7c85d79255853b0d310","source":{"kind":"arxiv","id":"2205.07100","version":1},"attestation_state":"computed","paper":{"title":"Multiformer: A Head-Configurable Transformer-Based Model for Direct Speech Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Belen Alastruey, Gerard I. G\\'allego, Gerard Sant, Marta R. Costa-juss\\`a","submitted_at":"2022-05-14T17:37:47Z","abstract_excerpt":"Transformer-based models have been achieving state-of-the-art results in several fields of Natural Language Processing. However, its direct application to speech tasks is not trivial. The nature of this sequences carries problems such as long sequence lengths and redundancy between adjacent tokens. Therefore, we believe that regular self-attention mechanism might not be well suited for it.\n  Different approaches have been proposed to overcome these problems, such as the use of efficient attention mechanisms. However, the use of these methods usually comes with a cost, which is a performance re"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2205.07100","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-14T17:37:47Z","cross_cats_sorted":["cs.AI","cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"b5304be831871fd974a9dc4b6001feccf4344cbbfe725752e55bf0523d877fd8","abstract_canon_sha256":"cfb3aa09f3438f0dce99ea136b868a9f1dfba875a1399c7a801bb3aceb7f156d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:23:12.040835Z","signature_b64":"Nv+cwnqrOLawOhrvpr3CTXefLaE+IOcqo4p8/tvhTlGbhhg0yVWoqbajxV1cyxyNJ8hRZQ26VW4gOQD7iXR1Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c71746c8e80c5519939002648b4a9aa6a1f9df6c412cc7c85d79255853b0d310","last_reissued_at":"2026-07-05T04:23:12.040335Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:23:12.040335Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multiformer: A Head-Configurable Transformer-Based Model for Direct Speech Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Belen Alastruey, Gerard I. G\\'allego, Gerard Sant, Marta R. Costa-juss\\`a","submitted_at":"2022-05-14T17:37:47Z","abstract_excerpt":"Transformer-based models have been achieving state-of-the-art results in several fields of Natural Language Processing. However, its direct application to speech tasks is not trivial. The nature of this sequences carries problems such as long sequence lengths and redundancy between adjacent tokens. Therefore, we believe that regular self-attention mechanism might not be well suited for it.\n  Different approaches have been proposed to overcome these problems, such as the use of efficient attention mechanisms. However, the use of these methods usually comes with a cost, which is a performance re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.07100","kind":"arxiv","version":1},"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/2205.07100/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2205.07100","created_at":"2026-07-05T04:23:12.040411+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.07100v1","created_at":"2026-07-05T04:23:12.040411+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.07100","created_at":"2026-07-05T04:23:12.040411+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y4LUNSHIBRKR","created_at":"2026-07-05T04:23:12.040411+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y4LUNSHIBRKRTE4Q","created_at":"2026-07-05T04:23:12.040411+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y4LUNSHI","created_at":"2026-07-05T04:23:12.040411+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y4LUNSHIBRKRTE4QAJSIWSU2U2","json":"https://pith.science/pith/Y4LUNSHIBRKRTE4QAJSIWSU2U2.json","graph_json":"https://pith.science/api/pith-number/Y4LUNSHIBRKRTE4QAJSIWSU2U2/graph.json","events_json":"https://pith.science/api/pith-number/Y4LUNSHIBRKRTE4QAJSIWSU2U2/events.json","paper":"https://pith.science/paper/Y4LUNSHI"},"agent_actions":{"view_html":"https://pith.science/pith/Y4LUNSHIBRKRTE4QAJSIWSU2U2","download_json":"https://pith.science/pith/Y4LUNSHIBRKRTE4QAJSIWSU2U2.json","view_paper":"https://pith.science/paper/Y4LUNSHI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.07100&json=true","fetch_graph":"https://pith.science/api/pith-number/Y4LUNSHIBRKRTE4QAJSIWSU2U2/graph.json","fetch_events":"https://pith.science/api/pith-number/Y4LUNSHIBRKRTE4QAJSIWSU2U2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y4LUNSHIBRKRTE4QAJSIWSU2U2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y4LUNSHIBRKRTE4QAJSIWSU2U2/action/storage_attestation","attest_author":"https://pith.science/pith/Y4LUNSHIBRKRTE4QAJSIWSU2U2/action/author_attestation","sign_citation":"https://pith.science/pith/Y4LUNSHIBRKRTE4QAJSIWSU2U2/action/citation_signature","submit_replication":"https://pith.science/pith/Y4LUNSHIBRKRTE4QAJSIWSU2U2/action/replication_record"}},"created_at":"2026-07-05T04:23:12.040411+00:00","updated_at":"2026-07-05T04:23:12.040411+00:00"}