{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UJE2KAGYJVKOOBC4AZ4D34M3EF","short_pith_number":"pith:UJE2KAGY","schema_version":"1.0","canonical_sha256":"a249a500d84d54e7045c06783df19b21711ac1b51d4b0d79c95ea6e2532d6aa0","source":{"kind":"arxiv","id":"2411.18388","version":1},"attestation_state":"computed","paper":{"title":"Convolutional Neural Networks Do Work with Pre-Defined Filters","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Christoph Linse, Erhardt Barth, Thomas Martinetz","submitted_at":"2024-11-27T14:30:44Z","abstract_excerpt":"We present a novel class of Convolutional Neural Networks called Pre-defined Filter Convolutional Neural Networks (PFCNNs), where all nxn convolution kernels with n>1 are pre-defined and constant during training. It involves a special form of depthwise convolution operation called a Pre-defined Filter Module (PFM). In the channel-wise convolution part, the 1xnxn kernels are drawn from a fixed pool of only a few (16) different pre-defined kernels. In the 1x1 convolution part linear combinations of the pre-defined filter outputs are learned. Despite this harsh restriction, complex and discrimina"},"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":"2411.18388","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-27T14:30:44Z","cross_cats_sorted":[],"title_canon_sha256":"ade25b690803ba866494ec259341cf592bc9ef3db96339646c2e4c02ed038585","abstract_canon_sha256":"3ad1213fc6ccba3a4bcc4c25bd719f3ab1c73c3fb91eb5de736d7e124d79bd22"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:41:15.942665Z","signature_b64":"wIgwRsLKHcAqWbynLnOpR9Wx6Qg4SMILVorW0me0SomNVpg8/6IrOm69uxNsH3VPR72Pl+qdPD8nddrPTITZDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a249a500d84d54e7045c06783df19b21711ac1b51d4b0d79c95ea6e2532d6aa0","last_reissued_at":"2026-07-05T09:41:15.942220Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:41:15.942220Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Convolutional Neural Networks Do Work with Pre-Defined Filters","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Christoph Linse, Erhardt Barth, Thomas Martinetz","submitted_at":"2024-11-27T14:30:44Z","abstract_excerpt":"We present a novel class of Convolutional Neural Networks called Pre-defined Filter Convolutional Neural Networks (PFCNNs), where all nxn convolution kernels with n>1 are pre-defined and constant during training. It involves a special form of depthwise convolution operation called a Pre-defined Filter Module (PFM). In the channel-wise convolution part, the 1xnxn kernels are drawn from a fixed pool of only a few (16) different pre-defined kernels. In the 1x1 convolution part linear combinations of the pre-defined filter outputs are learned. Despite this harsh restriction, complex and discrimina"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.18388","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/2411.18388/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":"2411.18388","created_at":"2026-07-05T09:41:15.942275+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.18388v1","created_at":"2026-07-05T09:41:15.942275+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.18388","created_at":"2026-07-05T09:41:15.942275+00:00"},{"alias_kind":"pith_short_12","alias_value":"UJE2KAGYJVKO","created_at":"2026-07-05T09:41:15.942275+00:00"},{"alias_kind":"pith_short_16","alias_value":"UJE2KAGYJVKOOBC4","created_at":"2026-07-05T09:41:15.942275+00:00"},{"alias_kind":"pith_short_8","alias_value":"UJE2KAGY","created_at":"2026-07-05T09:41:15.942275+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/UJE2KAGYJVKOOBC4AZ4D34M3EF","json":"https://pith.science/pith/UJE2KAGYJVKOOBC4AZ4D34M3EF.json","graph_json":"https://pith.science/api/pith-number/UJE2KAGYJVKOOBC4AZ4D34M3EF/graph.json","events_json":"https://pith.science/api/pith-number/UJE2KAGYJVKOOBC4AZ4D34M3EF/events.json","paper":"https://pith.science/paper/UJE2KAGY"},"agent_actions":{"view_html":"https://pith.science/pith/UJE2KAGYJVKOOBC4AZ4D34M3EF","download_json":"https://pith.science/pith/UJE2KAGYJVKOOBC4AZ4D34M3EF.json","view_paper":"https://pith.science/paper/UJE2KAGY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.18388&json=true","fetch_graph":"https://pith.science/api/pith-number/UJE2KAGYJVKOOBC4AZ4D34M3EF/graph.json","fetch_events":"https://pith.science/api/pith-number/UJE2KAGYJVKOOBC4AZ4D34M3EF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UJE2KAGYJVKOOBC4AZ4D34M3EF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UJE2KAGYJVKOOBC4AZ4D34M3EF/action/storage_attestation","attest_author":"https://pith.science/pith/UJE2KAGYJVKOOBC4AZ4D34M3EF/action/author_attestation","sign_citation":"https://pith.science/pith/UJE2KAGYJVKOOBC4AZ4D34M3EF/action/citation_signature","submit_replication":"https://pith.science/pith/UJE2KAGYJVKOOBC4AZ4D34M3EF/action/replication_record"}},"created_at":"2026-07-05T09:41:15.942275+00:00","updated_at":"2026-07-05T09:41:15.942275+00:00"}