{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6DM3Q4C6RPZOFPW3ROBIHRG7PN","short_pith_number":"pith:6DM3Q4C6","schema_version":"1.0","canonical_sha256":"f0d9b8705e8bf2e2bedb8b8283c4df7b6547b591ea8739119dd0e4b2b244a66d","source":{"kind":"arxiv","id":"2606.24371","version":1},"attestation_state":"computed","paper":{"title":"Structural Kolmogorov-Arnold Convolutions: Learnable Function on the Values or the Filter Shape as Parameter-Efficient Alternative to Per-Edge Convolutional KANs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Adriano Mancini, Alessandro Galdelli, Emanuele Frontoni, Ferdinando Cannella, Gabriele Marchello, Oleksandr Kuznetsov, Stefano Mereu","submitted_at":"2026-06-23T10:00:26Z","abstract_excerpt":"Convolutional Kolmogorov--Arnold Networks (KANs) replace the fixed weights of a convolutional kernel with learnable univariate functions. The dominant formulation attaches one such function to every kernel entry and lets it act on pixel values, expressive but parameter-heavy and prone to overfitting. We argue that the learnable functions are better placed in the \\emph{structure} of the convolution than on each edge, and we organise the design space along a single axis: whether the function acts on the pixel \\emph{values} or on the filter \\emph{shape}. We study three realisations. SV-KAN applie"},"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":"2606.24371","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-23T10:00:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"718eebc88549e4c083b863241e2bd887d30c0842f107e72332b4b47f09be184a","abstract_canon_sha256":"071f79c26bec54a229b300cdda0e91988067b465f0c10cbf550942203269b568"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-24T01:15:28.795999Z","signature_b64":"bYawKLd43Vb02vXVieGKzTTNF/E6BAT5dnyE0sbTbjLCzbgJXyr0ryablbN/LwJEub4ZvoS6WDBppphyc1CsAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0d9b8705e8bf2e2bedb8b8283c4df7b6547b591ea8739119dd0e4b2b244a66d","last_reissued_at":"2026-06-24T01:15:28.795654Z","signature_status":"signed_v1","first_computed_at":"2026-06-24T01:15:28.795654Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Structural Kolmogorov-Arnold Convolutions: Learnable Function on the Values or the Filter Shape as Parameter-Efficient Alternative to Per-Edge Convolutional KANs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Adriano Mancini, Alessandro Galdelli, Emanuele Frontoni, Ferdinando Cannella, Gabriele Marchello, Oleksandr Kuznetsov, Stefano Mereu","submitted_at":"2026-06-23T10:00:26Z","abstract_excerpt":"Convolutional Kolmogorov--Arnold Networks (KANs) replace the fixed weights of a convolutional kernel with learnable univariate functions. The dominant formulation attaches one such function to every kernel entry and lets it act on pixel values, expressive but parameter-heavy and prone to overfitting. We argue that the learnable functions are better placed in the \\emph{structure} of the convolution than on each edge, and we organise the design space along a single axis: whether the function acts on the pixel \\emph{values} or on the filter \\emph{shape}. We study three realisations. SV-KAN applie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.24371","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/2606.24371/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":"2606.24371","created_at":"2026-06-24T01:15:28.795718+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.24371v1","created_at":"2026-06-24T01:15:28.795718+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.24371","created_at":"2026-06-24T01:15:28.795718+00:00"},{"alias_kind":"pith_short_12","alias_value":"6DM3Q4C6RPZO","created_at":"2026-06-24T01:15:28.795718+00:00"},{"alias_kind":"pith_short_16","alias_value":"6DM3Q4C6RPZOFPW3","created_at":"2026-06-24T01:15:28.795718+00:00"},{"alias_kind":"pith_short_8","alias_value":"6DM3Q4C6","created_at":"2026-06-24T01:15:28.795718+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/6DM3Q4C6RPZOFPW3ROBIHRG7PN","json":"https://pith.science/pith/6DM3Q4C6RPZOFPW3ROBIHRG7PN.json","graph_json":"https://pith.science/api/pith-number/6DM3Q4C6RPZOFPW3ROBIHRG7PN/graph.json","events_json":"https://pith.science/api/pith-number/6DM3Q4C6RPZOFPW3ROBIHRG7PN/events.json","paper":"https://pith.science/paper/6DM3Q4C6"},"agent_actions":{"view_html":"https://pith.science/pith/6DM3Q4C6RPZOFPW3ROBIHRG7PN","download_json":"https://pith.science/pith/6DM3Q4C6RPZOFPW3ROBIHRG7PN.json","view_paper":"https://pith.science/paper/6DM3Q4C6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.24371&json=true","fetch_graph":"https://pith.science/api/pith-number/6DM3Q4C6RPZOFPW3ROBIHRG7PN/graph.json","fetch_events":"https://pith.science/api/pith-number/6DM3Q4C6RPZOFPW3ROBIHRG7PN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6DM3Q4C6RPZOFPW3ROBIHRG7PN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6DM3Q4C6RPZOFPW3ROBIHRG7PN/action/storage_attestation","attest_author":"https://pith.science/pith/6DM3Q4C6RPZOFPW3ROBIHRG7PN/action/author_attestation","sign_citation":"https://pith.science/pith/6DM3Q4C6RPZOFPW3ROBIHRG7PN/action/citation_signature","submit_replication":"https://pith.science/pith/6DM3Q4C6RPZOFPW3ROBIHRG7PN/action/replication_record"}},"created_at":"2026-06-24T01:15:28.795718+00:00","updated_at":"2026-06-24T01:15:28.795718+00:00"}