{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:P6A34HKZHB22RFWIF6FCI4BSAD","short_pith_number":"pith:P6A34HKZ","schema_version":"1.0","canonical_sha256":"7f81be1d593875a896c82f8a24703200cf19b25ce73ca3d893217352bad25207","source":{"kind":"arxiv","id":"2407.05848","version":2},"attestation_state":"computed","paper":{"title":"Wavelet Convolutions for Large Receptive Fields","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Eran Treister, Oren Freifeld, Roy Amoyal, Shahaf E. Finder","submitted_at":"2024-07-08T11:55:10Z","abstract_excerpt":"In recent years, there have been attempts to increase the kernel size of Convolutional Neural Nets (CNNs) to mimic the global receptive field of Vision Transformers' (ViTs) self-attention blocks. That approach, however, quickly hit an upper bound and saturated way before achieving a global receptive field. In this work, we demonstrate that by leveraging the Wavelet Transform (WT), it is, in fact, possible to obtain very large receptive fields without suffering from over-parameterization, e.g., for a $k \\times k$ receptive field, the number of trainable parameters in the proposed method grows o"},"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":"2407.05848","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-08T11:55:10Z","cross_cats_sorted":[],"title_canon_sha256":"567bcce34a4f8eec3b917f4ad51851ab3605891791ea958406281b7838569688","abstract_canon_sha256":"7e406badbde31ec0cc814a44e9dbdf31356a5eadcda984c3d12f36ab56cfe80e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:43:57.134341Z","signature_b64":"OVUvcF4dJf0NH9AoFpeR1LrN7xcR6gmxqhV45V/aD5T4SvmccDFSt4QU/TUIGMDarYPknFmpkIuQiZD3yt20Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f81be1d593875a896c82f8a24703200cf19b25ce73ca3d893217352bad25207","last_reissued_at":"2026-07-05T08:43:57.133849Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:43:57.133849Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Wavelet Convolutions for Large Receptive Fields","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Eran Treister, Oren Freifeld, Roy Amoyal, Shahaf E. Finder","submitted_at":"2024-07-08T11:55:10Z","abstract_excerpt":"In recent years, there have been attempts to increase the kernel size of Convolutional Neural Nets (CNNs) to mimic the global receptive field of Vision Transformers' (ViTs) self-attention blocks. That approach, however, quickly hit an upper bound and saturated way before achieving a global receptive field. In this work, we demonstrate that by leveraging the Wavelet Transform (WT), it is, in fact, possible to obtain very large receptive fields without suffering from over-parameterization, e.g., for a $k \\times k$ receptive field, the number of trainable parameters in the proposed method grows o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.05848","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/2407.05848/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":"2407.05848","created_at":"2026-07-05T08:43:57.133906+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.05848v2","created_at":"2026-07-05T08:43:57.133906+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.05848","created_at":"2026-07-05T08:43:57.133906+00:00"},{"alias_kind":"pith_short_12","alias_value":"P6A34HKZHB22","created_at":"2026-07-05T08:43:57.133906+00:00"},{"alias_kind":"pith_short_16","alias_value":"P6A34HKZHB22RFWI","created_at":"2026-07-05T08:43:57.133906+00:00"},{"alias_kind":"pith_short_8","alias_value":"P6A34HKZ","created_at":"2026-07-05T08:43:57.133906+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.04127","citing_title":"SARES-DEIM: Sparse Mixture-of-Experts Meets DETR for Robust SAR Ship Detection","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P6A34HKZHB22RFWIF6FCI4BSAD","json":"https://pith.science/pith/P6A34HKZHB22RFWIF6FCI4BSAD.json","graph_json":"https://pith.science/api/pith-number/P6A34HKZHB22RFWIF6FCI4BSAD/graph.json","events_json":"https://pith.science/api/pith-number/P6A34HKZHB22RFWIF6FCI4BSAD/events.json","paper":"https://pith.science/paper/P6A34HKZ"},"agent_actions":{"view_html":"https://pith.science/pith/P6A34HKZHB22RFWIF6FCI4BSAD","download_json":"https://pith.science/pith/P6A34HKZHB22RFWIF6FCI4BSAD.json","view_paper":"https://pith.science/paper/P6A34HKZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.05848&json=true","fetch_graph":"https://pith.science/api/pith-number/P6A34HKZHB22RFWIF6FCI4BSAD/graph.json","fetch_events":"https://pith.science/api/pith-number/P6A34HKZHB22RFWIF6FCI4BSAD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P6A34HKZHB22RFWIF6FCI4BSAD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P6A34HKZHB22RFWIF6FCI4BSAD/action/storage_attestation","attest_author":"https://pith.science/pith/P6A34HKZHB22RFWIF6FCI4BSAD/action/author_attestation","sign_citation":"https://pith.science/pith/P6A34HKZHB22RFWIF6FCI4BSAD/action/citation_signature","submit_replication":"https://pith.science/pith/P6A34HKZHB22RFWIF6FCI4BSAD/action/replication_record"}},"created_at":"2026-07-05T08:43:57.133906+00:00","updated_at":"2026-07-05T08:43:57.133906+00:00"}