{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:T4VZ5GD6SWGP7UWRFVJIRHYCVY","short_pith_number":"pith:T4VZ5GD6","schema_version":"1.0","canonical_sha256":"9f2b9e987e958cffd2d12d52889f02ae22ba9d90cb351317e63869a1fd0ebfe0","source":{"kind":"arxiv","id":"2002.03184","version":2},"attestation_state":"computed","paper":{"title":"Time-aware Large Kernel Convolutions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Vasileios Lioutas, Yuhong Guo","submitted_at":"2020-02-08T15:30:28Z","abstract_excerpt":"To date, most state-of-the-art sequence modeling architectures use attention to build generative models for language based tasks. Some of these models use all the available sequence tokens to generate an attention distribution which results in time complexity of $O(n^2)$. Alternatively, they utilize depthwise convolutions with softmax normalized kernels of size $k$ acting as a limited-window self-attention, resulting in time complexity of $O(k{\\cdot}n)$. In this paper, we introduce Time-aware Large Kernel (TaLK) Convolutions, a novel adaptive convolution operation that learns to predict the si"},"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":"2002.03184","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-08T15:30:28Z","cross_cats_sorted":["cs.CL","stat.ML"],"title_canon_sha256":"128ea25ee71cc048ba60426b5091e244ac0e309a543c853c408c66abef16dae8","abstract_canon_sha256":"303ece40a4a4f2cb4d8494b5a9846b119e009818d1826d95e91391a11001e2a5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:11:24.124103Z","signature_b64":"AYCH9oATrNljaCZr2jQmA/oY0nj+0bybvjHRLpMPiQ9SJL94gIQWze/TBemwGJyeqnWH4F4lxn5flWqyX6L/Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f2b9e987e958cffd2d12d52889f02ae22ba9d90cb351317e63869a1fd0ebfe0","last_reissued_at":"2026-07-05T01:11:24.123713Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:11:24.123713Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Time-aware Large Kernel Convolutions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Vasileios Lioutas, Yuhong Guo","submitted_at":"2020-02-08T15:30:28Z","abstract_excerpt":"To date, most state-of-the-art sequence modeling architectures use attention to build generative models for language based tasks. Some of these models use all the available sequence tokens to generate an attention distribution which results in time complexity of $O(n^2)$. Alternatively, they utilize depthwise convolutions with softmax normalized kernels of size $k$ acting as a limited-window self-attention, resulting in time complexity of $O(k{\\cdot}n)$. In this paper, we introduce Time-aware Large Kernel (TaLK) Convolutions, a novel adaptive convolution operation that learns to predict the si"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.03184","kind":"arxiv","version":2},"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/2002.03184/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":"2002.03184","created_at":"2026-07-05T01:11:24.123765+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.03184v2","created_at":"2026-07-05T01:11:24.123765+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.03184","created_at":"2026-07-05T01:11:24.123765+00:00"},{"alias_kind":"pith_short_12","alias_value":"T4VZ5GD6SWGP","created_at":"2026-07-05T01:11:24.123765+00:00"},{"alias_kind":"pith_short_16","alias_value":"T4VZ5GD6SWGP7UWR","created_at":"2026-07-05T01:11:24.123765+00:00"},{"alias_kind":"pith_short_8","alias_value":"T4VZ5GD6","created_at":"2026-07-05T01:11:24.123765+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/T4VZ5GD6SWGP7UWRFVJIRHYCVY","json":"https://pith.science/pith/T4VZ5GD6SWGP7UWRFVJIRHYCVY.json","graph_json":"https://pith.science/api/pith-number/T4VZ5GD6SWGP7UWRFVJIRHYCVY/graph.json","events_json":"https://pith.science/api/pith-number/T4VZ5GD6SWGP7UWRFVJIRHYCVY/events.json","paper":"https://pith.science/paper/T4VZ5GD6"},"agent_actions":{"view_html":"https://pith.science/pith/T4VZ5GD6SWGP7UWRFVJIRHYCVY","download_json":"https://pith.science/pith/T4VZ5GD6SWGP7UWRFVJIRHYCVY.json","view_paper":"https://pith.science/paper/T4VZ5GD6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.03184&json=true","fetch_graph":"https://pith.science/api/pith-number/T4VZ5GD6SWGP7UWRFVJIRHYCVY/graph.json","fetch_events":"https://pith.science/api/pith-number/T4VZ5GD6SWGP7UWRFVJIRHYCVY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T4VZ5GD6SWGP7UWRFVJIRHYCVY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T4VZ5GD6SWGP7UWRFVJIRHYCVY/action/storage_attestation","attest_author":"https://pith.science/pith/T4VZ5GD6SWGP7UWRFVJIRHYCVY/action/author_attestation","sign_citation":"https://pith.science/pith/T4VZ5GD6SWGP7UWRFVJIRHYCVY/action/citation_signature","submit_replication":"https://pith.science/pith/T4VZ5GD6SWGP7UWRFVJIRHYCVY/action/replication_record"}},"created_at":"2026-07-05T01:11:24.123765+00:00","updated_at":"2026-07-05T01:11:24.123765+00:00"}