{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:CZ7W2JNWJZALMED4YWJL34E5BP","short_pith_number":"pith:CZ7W2JNW","canonical_record":{"source":{"id":"2505.18131","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-23T17:41:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"68e93e8e39ca45ae81eb0200315a3277e21955d34dad6f84b86c06d5968affa2","abstract_canon_sha256":"1d20238a72aa1c72dbf2c985fd306d988cf2f3e3c2f413322d9d036cfd2d1195"},"schema_version":"1.0"},"canonical_sha256":"167f6d25b64e40b6107cc592bdf09d0be879d921612066ccfd145bbcd489ff00","source":{"kind":"arxiv","id":"2505.18131","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.18131","created_at":"2026-07-05T11:08:36Z"},{"alias_kind":"arxiv_version","alias_value":"2505.18131v1","created_at":"2026-07-05T11:08:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18131","created_at":"2026-07-05T11:08:36Z"},{"alias_kind":"pith_short_12","alias_value":"CZ7W2JNWJZAL","created_at":"2026-07-05T11:08:36Z"},{"alias_kind":"pith_short_16","alias_value":"CZ7W2JNWJZALMED4","created_at":"2026-07-05T11:08:36Z"},{"alias_kind":"pith_short_8","alias_value":"CZ7W2JNW","created_at":"2026-07-05T11:08:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:CZ7W2JNWJZALMED4YWJL34E5BP","target":"record","payload":{"canonical_record":{"source":{"id":"2505.18131","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-23T17:41:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"68e93e8e39ca45ae81eb0200315a3277e21955d34dad6f84b86c06d5968affa2","abstract_canon_sha256":"1d20238a72aa1c72dbf2c985fd306d988cf2f3e3c2f413322d9d036cfd2d1195"},"schema_version":"1.0"},"canonical_sha256":"167f6d25b64e40b6107cc592bdf09d0be879d921612066ccfd145bbcd489ff00","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:08:36.994607Z","signature_b64":"vl5IsTIAiBKkvafbudZbaEBnIdSChcZxyDS+/BK0t0isN9mow86UPujOCnFI+nV35wSd2xvcyzcW9B9uFybQDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"167f6d25b64e40b6107cc592bdf09d0be879d921612066ccfd145bbcd489ff00","last_reissued_at":"2026-07-05T11:08:36.994145Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:08:36.994145Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.18131","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:08:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yp6xgUJ6duEAewSQ5WUcVs91UFn4CG9tkTOoTN7JELFisPiaywRxjiEBeQoOXxfO30fCUbJzsbuM6JpvdALSCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T05:50:42.177563Z"},"content_sha256":"53a1287cfe44e818f19e1dd9726e29e2d8d25264887aaf531d886309bf507404","schema_version":"1.0","event_id":"sha256:53a1287cfe44e818f19e1dd9726e29e2d8d25264887aaf531d886309bf507404"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:CZ7W2JNWJZALMED4YWJL34E5BP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Leveraging KANs for Expedient Training of Multichannel MLPs via Preconditioning and Geometric Refinement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ben Southworth, Eric C. Cyr, Graham Harper, Jonas A. Actor","submitted_at":"2025-05-23T17:41:18Z","abstract_excerpt":"Multilayer perceptrons (MLPs) are a workhorse machine learning architecture, used in a variety of modern deep learning frameworks. However, recently Kolmogorov-Arnold Networks (KANs) have become increasingly popular due to their success on a range of problems, particularly for scientific machine learning tasks. In this paper, we exploit the relationship between KANs and multichannel MLPs to gain structural insight into how to train MLPs faster. We demonstrate the KAN basis (1) provides geometric localized support, and (2) acts as a preconditioned descent in the ReLU basis, overall resulting in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18131","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/2505.18131/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:08:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fGF3tSX/sLNVySqJBwnl8trUy24oW2rzViJcK0+6Z/MY1xAKG/XBrROnGuWn4Hiqh1S7IUZpvUMIBDWCDPPMCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T05:50:42.178057Z"},"content_sha256":"a2a4b6c4151f2e82943e426126472c1237c0d32c41897e9ed4a63a70554189af","schema_version":"1.0","event_id":"sha256:a2a4b6c4151f2e82943e426126472c1237c0d32c41897e9ed4a63a70554189af"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CZ7W2JNWJZALMED4YWJL34E5BP/bundle.json","state_url":"https://pith.science/pith/CZ7W2JNWJZALMED4YWJL34E5BP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CZ7W2JNWJZALMED4YWJL34E5BP/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T05:50:42Z","links":{"resolver":"https://pith.science/pith/CZ7W2JNWJZALMED4YWJL34E5BP","bundle":"https://pith.science/pith/CZ7W2JNWJZALMED4YWJL34E5BP/bundle.json","state":"https://pith.science/pith/CZ7W2JNWJZALMED4YWJL34E5BP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CZ7W2JNWJZALMED4YWJL34E5BP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CZ7W2JNWJZALMED4YWJL34E5BP","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"1d20238a72aa1c72dbf2c985fd306d988cf2f3e3c2f413322d9d036cfd2d1195","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-23T17:41:18Z","title_canon_sha256":"68e93e8e39ca45ae81eb0200315a3277e21955d34dad6f84b86c06d5968affa2"},"schema_version":"1.0","source":{"id":"2505.18131","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.18131","created_at":"2026-07-05T11:08:36Z"},{"alias_kind":"arxiv_version","alias_value":"2505.18131v1","created_at":"2026-07-05T11:08:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18131","created_at":"2026-07-05T11:08:36Z"},{"alias_kind":"pith_short_12","alias_value":"CZ7W2JNWJZAL","created_at":"2026-07-05T11:08:36Z"},{"alias_kind":"pith_short_16","alias_value":"CZ7W2JNWJZALMED4","created_at":"2026-07-05T11:08:36Z"},{"alias_kind":"pith_short_8","alias_value":"CZ7W2JNW","created_at":"2026-07-05T11:08:36Z"}],"graph_snapshots":[{"event_id":"sha256:a2a4b6c4151f2e82943e426126472c1237c0d32c41897e9ed4a63a70554189af","target":"graph","created_at":"2026-07-05T11:08:36Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.18131/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multilayer perceptrons (MLPs) are a workhorse machine learning architecture, used in a variety of modern deep learning frameworks. However, recently Kolmogorov-Arnold Networks (KANs) have become increasingly popular due to their success on a range of problems, particularly for scientific machine learning tasks. In this paper, we exploit the relationship between KANs and multichannel MLPs to gain structural insight into how to train MLPs faster. We demonstrate the KAN basis (1) provides geometric localized support, and (2) acts as a preconditioned descent in the ReLU basis, overall resulting in","authors_text":"Ben Southworth, Eric C. Cyr, Graham Harper, Jonas A. Actor","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-23T17:41:18Z","title":"Leveraging KANs for Expedient Training of Multichannel MLPs via Preconditioning and Geometric Refinement"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18131","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:53a1287cfe44e818f19e1dd9726e29e2d8d25264887aaf531d886309bf507404","target":"record","created_at":"2026-07-05T11:08:36Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"1d20238a72aa1c72dbf2c985fd306d988cf2f3e3c2f413322d9d036cfd2d1195","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-23T17:41:18Z","title_canon_sha256":"68e93e8e39ca45ae81eb0200315a3277e21955d34dad6f84b86c06d5968affa2"},"schema_version":"1.0","source":{"id":"2505.18131","kind":"arxiv","version":1}},"canonical_sha256":"167f6d25b64e40b6107cc592bdf09d0be879d921612066ccfd145bbcd489ff00","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"167f6d25b64e40b6107cc592bdf09d0be879d921612066ccfd145bbcd489ff00","first_computed_at":"2026-07-05T11:08:36.994145Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:08:36.994145Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vl5IsTIAiBKkvafbudZbaEBnIdSChcZxyDS+/BK0t0isN9mow86UPujOCnFI+nV35wSd2xvcyzcW9B9uFybQDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:08:36.994607Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.18131","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:53a1287cfe44e818f19e1dd9726e29e2d8d25264887aaf531d886309bf507404","sha256:a2a4b6c4151f2e82943e426126472c1237c0d32c41897e9ed4a63a70554189af"],"state_sha256":"838bf48fdb9f52f401cc0f4ef5b50729d9cf29ab3805f231f7de5107bb6ce002"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rR7cxorPMuJ9TqQesAzBRcG5dKk9p5L/CA8hahHAHsFT6OSk7Ao5gM1/iBMi+45H6MZ/skK/kmV1xQ4TFT3bBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T05:50:42.183461Z","bundle_sha256":"39ae6c95b94a8e90ddaa0c38626240720fe359e3f42fbddc7899a142bbbe6919"}}