{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LE3AVMY562JIN75FHCQFJBB2BN","short_pith_number":"pith:LE3AVMY5","schema_version":"1.0","canonical_sha256":"59360ab31df69286ffa538a054843a0b783676fc5cd9187e340d8f0e0f4aa651","source":{"kind":"arxiv","id":"2401.05738","version":3},"attestation_state":"computed","paper":{"title":"Interpreting and Improving Attention From the Perspective of Large Kernel Convolution","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boheng Zeng, Chaoning Zhang, Chenghao Li, Heng Tao Shen, Jirui Liu, Lingyun Zhu, Pengbo Shi, Qingzi Chen, Yang Yang, Yi Lu","submitted_at":"2024-01-11T08:40:35Z","abstract_excerpt":"Attention mechanisms have significantly advanced visual models by capturing global context effectively. However, their reliance on large-scale datasets and substantial computational resources poses challenges in data-scarce and resource-constrained scenarios. Moreover, traditional self-attention mechanisms lack inherent spatial inductive biases, making them suboptimal for modeling local features critical to tasks involving smaller datasets. In this work, we introduce Large Kernel Convolutional Attention (LKCA), a novel formulation that reinterprets attention operations as a single large-kernel"},"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":"2401.05738","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-11T08:40:35Z","cross_cats_sorted":[],"title_canon_sha256":"4cd6f291b8af3c06c923be45e923db04fd11320ff3d9953ed7634716861afca7","abstract_canon_sha256":"af532764158ff45918918390edd8dcfca49b47b3e64f834182759df5906f4521"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:42:22.003958Z","signature_b64":"tZlp03X4q475k28CGX0/nfl9oVIpYeIfE4Ew7wHQsNjzX+2XtQxKcmu7Q0CVvV6eB9aJf4zkUMfvjjhXp2QGDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59360ab31df69286ffa538a054843a0b783676fc5cd9187e340d8f0e0f4aa651","last_reissued_at":"2026-07-05T09:42:22.003453Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:42:22.003453Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Interpreting and Improving Attention From the Perspective of Large Kernel Convolution","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boheng Zeng, Chaoning Zhang, Chenghao Li, Heng Tao Shen, Jirui Liu, Lingyun Zhu, Pengbo Shi, Qingzi Chen, Yang Yang, Yi Lu","submitted_at":"2024-01-11T08:40:35Z","abstract_excerpt":"Attention mechanisms have significantly advanced visual models by capturing global context effectively. However, their reliance on large-scale datasets and substantial computational resources poses challenges in data-scarce and resource-constrained scenarios. Moreover, traditional self-attention mechanisms lack inherent spatial inductive biases, making them suboptimal for modeling local features critical to tasks involving smaller datasets. In this work, we introduce Large Kernel Convolutional Attention (LKCA), a novel formulation that reinterprets attention operations as a single large-kernel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.05738","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2401.05738/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":"2401.05738","created_at":"2026-07-05T09:42:22.003518+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.05738v3","created_at":"2026-07-05T09:42:22.003518+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.05738","created_at":"2026-07-05T09:42:22.003518+00:00"},{"alias_kind":"pith_short_12","alias_value":"LE3AVMY562JI","created_at":"2026-07-05T09:42:22.003518+00:00"},{"alias_kind":"pith_short_16","alias_value":"LE3AVMY562JIN75F","created_at":"2026-07-05T09:42:22.003518+00:00"},{"alias_kind":"pith_short_8","alias_value":"LE3AVMY5","created_at":"2026-07-05T09:42:22.003518+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/LE3AVMY562JIN75FHCQFJBB2BN","json":"https://pith.science/pith/LE3AVMY562JIN75FHCQFJBB2BN.json","graph_json":"https://pith.science/api/pith-number/LE3AVMY562JIN75FHCQFJBB2BN/graph.json","events_json":"https://pith.science/api/pith-number/LE3AVMY562JIN75FHCQFJBB2BN/events.json","paper":"https://pith.science/paper/LE3AVMY5"},"agent_actions":{"view_html":"https://pith.science/pith/LE3AVMY562JIN75FHCQFJBB2BN","download_json":"https://pith.science/pith/LE3AVMY562JIN75FHCQFJBB2BN.json","view_paper":"https://pith.science/paper/LE3AVMY5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.05738&json=true","fetch_graph":"https://pith.science/api/pith-number/LE3AVMY562JIN75FHCQFJBB2BN/graph.json","fetch_events":"https://pith.science/api/pith-number/LE3AVMY562JIN75FHCQFJBB2BN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LE3AVMY562JIN75FHCQFJBB2BN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LE3AVMY562JIN75FHCQFJBB2BN/action/storage_attestation","attest_author":"https://pith.science/pith/LE3AVMY562JIN75FHCQFJBB2BN/action/author_attestation","sign_citation":"https://pith.science/pith/LE3AVMY562JIN75FHCQFJBB2BN/action/citation_signature","submit_replication":"https://pith.science/pith/LE3AVMY562JIN75FHCQFJBB2BN/action/replication_record"}},"created_at":"2026-07-05T09:42:22.003518+00:00","updated_at":"2026-07-05T09:42:22.003518+00:00"}