{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:7OE7NLI35G44JSKFSXDGMR7UUR","short_pith_number":"pith:7OE7NLI3","schema_version":"1.0","canonical_sha256":"fb89f6ad1be9b9c4c94595c66647f4a4614a27d4d6069ba88733240629b828a8","source":{"kind":"arxiv","id":"1808.03867","version":3},"attestation_state":"computed","paper":{"title":"Pervasive Attention: 2D Convolutional Neural Networks for Sequence-to-Sequence Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jakob Verbeek, Laurent Besacier, Maha Elbayad","submitted_at":"2018-08-11T21:23:24Z","abstract_excerpt":"Current state-of-the-art machine translation systems are based on encoder-decoder architectures, that first encode the input sequence, and then generate an output sequence based on the input encoding. Both are interfaced with an attention mechanism that recombines a fixed encoding of the source tokens based on the decoder state. We propose an alternative approach which instead relies on a single 2D convolutional neural network across both sequences. Each layer of our network re-codes source tokens on the basis of the output sequence produced so far. Attention-like properties are therefore perv"},"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":"1808.03867","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-11T21:23:24Z","cross_cats_sorted":[],"title_canon_sha256":"8eced69f9303e30e521ff6a27b829c24f48c21b36cf23ec1f2756735a2dfa194","abstract_canon_sha256":"8cb828b5a843e5ab252c29d4c251c90dd573fbd8eaf05cdee8046acd047f4ee1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:47.073559Z","signature_b64":"aGTByB2rYFqb2BY/Ve/tgNxaRjYcp0NwvNy0IkO2w8swJ9dkH2LEh/3kxsa6y0Kg60dM0a2DtuioQhnemmRzBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb89f6ad1be9b9c4c94595c66647f4a4614a27d4d6069ba88733240629b828a8","last_reissued_at":"2026-05-18T00:01:47.072705Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:47.072705Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pervasive Attention: 2D Convolutional Neural Networks for Sequence-to-Sequence Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jakob Verbeek, Laurent Besacier, Maha Elbayad","submitted_at":"2018-08-11T21:23:24Z","abstract_excerpt":"Current state-of-the-art machine translation systems are based on encoder-decoder architectures, that first encode the input sequence, and then generate an output sequence based on the input encoding. Both are interfaced with an attention mechanism that recombines a fixed encoding of the source tokens based on the decoder state. We propose an alternative approach which instead relies on a single 2D convolutional neural network across both sequences. Each layer of our network re-codes source tokens on the basis of the output sequence produced so far. Attention-like properties are therefore perv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.03867","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1808.03867","created_at":"2026-05-18T00:01:47.072851+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.03867v3","created_at":"2026-05-18T00:01:47.072851+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.03867","created_at":"2026-05-18T00:01:47.072851+00:00"},{"alias_kind":"pith_short_12","alias_value":"7OE7NLI35G44","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_16","alias_value":"7OE7NLI35G44JSKF","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_8","alias_value":"7OE7NLI3","created_at":"2026-05-18T12:32:11.075285+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/7OE7NLI35G44JSKFSXDGMR7UUR","json":"https://pith.science/pith/7OE7NLI35G44JSKFSXDGMR7UUR.json","graph_json":"https://pith.science/api/pith-number/7OE7NLI35G44JSKFSXDGMR7UUR/graph.json","events_json":"https://pith.science/api/pith-number/7OE7NLI35G44JSKFSXDGMR7UUR/events.json","paper":"https://pith.science/paper/7OE7NLI3"},"agent_actions":{"view_html":"https://pith.science/pith/7OE7NLI35G44JSKFSXDGMR7UUR","download_json":"https://pith.science/pith/7OE7NLI35G44JSKFSXDGMR7UUR.json","view_paper":"https://pith.science/paper/7OE7NLI3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.03867&json=true","fetch_graph":"https://pith.science/api/pith-number/7OE7NLI35G44JSKFSXDGMR7UUR/graph.json","fetch_events":"https://pith.science/api/pith-number/7OE7NLI35G44JSKFSXDGMR7UUR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7OE7NLI35G44JSKFSXDGMR7UUR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7OE7NLI35G44JSKFSXDGMR7UUR/action/storage_attestation","attest_author":"https://pith.science/pith/7OE7NLI35G44JSKFSXDGMR7UUR/action/author_attestation","sign_citation":"https://pith.science/pith/7OE7NLI35G44JSKFSXDGMR7UUR/action/citation_signature","submit_replication":"https://pith.science/pith/7OE7NLI35G44JSKFSXDGMR7UUR/action/replication_record"}},"created_at":"2026-05-18T00:01:47.072851+00:00","updated_at":"2026-05-18T00:01:47.072851+00:00"}