{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:DF3BOG4Q5KXAS2J4V2G3RTT5PT","short_pith_number":"pith:DF3BOG4Q","schema_version":"1.0","canonical_sha256":"1976171b90eaae09693cae8db8ce7d7cceed7e6ef4fbc590af92a524f6c5deab","source":{"kind":"arxiv","id":"2204.09028","version":1},"attestation_state":"computed","paper":{"title":"On the Locality of Attention in Direct Speech Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Belen Alastruey, Gerard I. G\\'allego, Javier Ferrando, Marta R. Costa-juss\\`a","submitted_at":"2022-04-19T17:43:37Z","abstract_excerpt":"Transformers have achieved state-of-the-art results across multiple NLP tasks. However, the self-attention mechanism complexity scales quadratically with the sequence length, creating an obstacle for tasks involving long sequences, like in the speech domain. In this paper, we discuss the usefulness of self-attention for Direct Speech Translation. First, we analyze the layer-wise token contributions in the self-attention of the encoder, unveiling local diagonal patterns. To prove that some attention weights are avoidable, we propose to substitute the standard self-attention with a local efficie"},"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":"2204.09028","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-04-19T17:43:37Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"2f73d17e3abfd43d0b1f61d2309dcfbc85dbf177578d88cf464c35a6f827ff3f","abstract_canon_sha256":"7550979deae017856a1805b9b317d01cbcc5bd2e8d01166402d50effde6c3a26"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:16:10.083846Z","signature_b64":"2X39vLSPm6QJPNgKXR3CLCDLjZML6hjH0svaOJyD9r7ySXuk5KYWR2EfSo+/grS+Hlr9lbQ9PwTFvSGhZZxwAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1976171b90eaae09693cae8db8ce7d7cceed7e6ef4fbc590af92a524f6c5deab","last_reissued_at":"2026-07-05T04:16:10.083436Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:16:10.083436Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Locality of Attention in Direct Speech Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Belen Alastruey, Gerard I. G\\'allego, Javier Ferrando, Marta R. Costa-juss\\`a","submitted_at":"2022-04-19T17:43:37Z","abstract_excerpt":"Transformers have achieved state-of-the-art results across multiple NLP tasks. However, the self-attention mechanism complexity scales quadratically with the sequence length, creating an obstacle for tasks involving long sequences, like in the speech domain. In this paper, we discuss the usefulness of self-attention for Direct Speech Translation. First, we analyze the layer-wise token contributions in the self-attention of the encoder, unveiling local diagonal patterns. To prove that some attention weights are avoidable, we propose to substitute the standard self-attention with a local efficie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.09028","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/2204.09028/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":"2204.09028","created_at":"2026-07-05T04:16:10.083504+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.09028v1","created_at":"2026-07-05T04:16:10.083504+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.09028","created_at":"2026-07-05T04:16:10.083504+00:00"},{"alias_kind":"pith_short_12","alias_value":"DF3BOG4Q5KXA","created_at":"2026-07-05T04:16:10.083504+00:00"},{"alias_kind":"pith_short_16","alias_value":"DF3BOG4Q5KXAS2J4","created_at":"2026-07-05T04:16:10.083504+00:00"},{"alias_kind":"pith_short_8","alias_value":"DF3BOG4Q","created_at":"2026-07-05T04:16:10.083504+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/DF3BOG4Q5KXAS2J4V2G3RTT5PT","json":"https://pith.science/pith/DF3BOG4Q5KXAS2J4V2G3RTT5PT.json","graph_json":"https://pith.science/api/pith-number/DF3BOG4Q5KXAS2J4V2G3RTT5PT/graph.json","events_json":"https://pith.science/api/pith-number/DF3BOG4Q5KXAS2J4V2G3RTT5PT/events.json","paper":"https://pith.science/paper/DF3BOG4Q"},"agent_actions":{"view_html":"https://pith.science/pith/DF3BOG4Q5KXAS2J4V2G3RTT5PT","download_json":"https://pith.science/pith/DF3BOG4Q5KXAS2J4V2G3RTT5PT.json","view_paper":"https://pith.science/paper/DF3BOG4Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.09028&json=true","fetch_graph":"https://pith.science/api/pith-number/DF3BOG4Q5KXAS2J4V2G3RTT5PT/graph.json","fetch_events":"https://pith.science/api/pith-number/DF3BOG4Q5KXAS2J4V2G3RTT5PT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DF3BOG4Q5KXAS2J4V2G3RTT5PT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DF3BOG4Q5KXAS2J4V2G3RTT5PT/action/storage_attestation","attest_author":"https://pith.science/pith/DF3BOG4Q5KXAS2J4V2G3RTT5PT/action/author_attestation","sign_citation":"https://pith.science/pith/DF3BOG4Q5KXAS2J4V2G3RTT5PT/action/citation_signature","submit_replication":"https://pith.science/pith/DF3BOG4Q5KXAS2J4V2G3RTT5PT/action/replication_record"}},"created_at":"2026-07-05T04:16:10.083504+00:00","updated_at":"2026-07-05T04:16:10.083504+00:00"}