{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:B36XH6FCU5ZO67FGBVVXBIKWZR","short_pith_number":"pith:B36XH6FC","canonical_record":{"source":{"id":"2504.07633","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-10T10:27:43Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"9620fd9b3733cc3684d4b72a1f8842b130d69f7f89ea3a167a0f8ce80884d080","abstract_canon_sha256":"ed4353e84aca7ea1a1194b6f3198a61d15a8a40fe4566cdfbea655f4755e61dc"},"schema_version":"1.0"},"canonical_sha256":"0efd73f8a2a772ef7ca60d6b70a156cc4fa3626afb2cf8fa2bb62a00c00e702d","source":{"kind":"arxiv","id":"2504.07633","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.07633","created_at":"2026-07-05T11:20:52Z"},{"alias_kind":"arxiv_version","alias_value":"2504.07633v3","created_at":"2026-07-05T11:20:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.07633","created_at":"2026-07-05T11:20:52Z"},{"alias_kind":"pith_short_12","alias_value":"B36XH6FCU5ZO","created_at":"2026-07-05T11:20:52Z"},{"alias_kind":"pith_short_16","alias_value":"B36XH6FCU5ZO67FG","created_at":"2026-07-05T11:20:52Z"},{"alias_kind":"pith_short_8","alias_value":"B36XH6FC","created_at":"2026-07-05T11:20:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:B36XH6FCU5ZO67FGBVVXBIKWZR","target":"record","payload":{"canonical_record":{"source":{"id":"2504.07633","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-10T10:27:43Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"9620fd9b3733cc3684d4b72a1f8842b130d69f7f89ea3a167a0f8ce80884d080","abstract_canon_sha256":"ed4353e84aca7ea1a1194b6f3198a61d15a8a40fe4566cdfbea655f4755e61dc"},"schema_version":"1.0"},"canonical_sha256":"0efd73f8a2a772ef7ca60d6b70a156cc4fa3626afb2cf8fa2bb62a00c00e702d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:20:52.555790Z","signature_b64":"6xiAxVLxDgDdxQXR05xKxDE0kEozOqUcSnG5lUNRFxRTnb2IB010hkie66hO9GROD+luXN75VAUji6gEDYoaDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0efd73f8a2a772ef7ca60d6b70a156cc4fa3626afb2cf8fa2bb62a00c00e702d","last_reissued_at":"2026-07-05T11:20:52.555179Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:20:52.555179Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.07633","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:20:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UvGyIkBOyF4FWRbWYzoz4VGN3gkZkSD+gHBFl7YSLL6qcJ7wekvESZB9huG9WVSG4ubPAvm/o5vESzOpIt2iBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T16:16:27.798377Z"},"content_sha256":"75494c463eb7c59d0f49eef1373fc80b6097f458071824bdbef5a5c40f6653cb","schema_version":"1.0","event_id":"sha256:75494c463eb7c59d0f49eef1373fc80b6097f458071824bdbef5a5c40f6653cb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:B36XH6FCU5ZO67FGBVVXBIKWZR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Kernel Logistic Regression Learning for High-Capacity Hopfield Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Akira Tamamori","submitted_at":"2025-04-10T10:27:43Z","abstract_excerpt":"Hebbian learning limits Hopfield network storage capacity (pattern-to-neuron ratio around 0.14). We propose Kernel Logistic Regression (KLR) learning. Unlike linear methods, KLR uses kernels to implicitly map patterns to high-dimensional feature space, enhancing separability. By learning dual variables, KLR dramatically improves storage capacity, achieving perfect recall even when pattern numbers exceed neuron numbers (up to ratio 1.5 shown), and enhances noise robustness. KLR demonstrably outperforms Hebbian and linear logistic regression approaches."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.07633","kind":"arxiv","version":3},"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/2504.07633/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":"2026-07-05T11:20:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R9vgfZDdUg8wEf7bSRrz+izAlq27uJ8ETJAuyiIlvy559xrDi7iBn+SdFu/qLSChCTcNx3paxl/u+3xtH34QCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T16:16:27.798756Z"},"content_sha256":"c0c65c4e01256a86a0520b981e3448b9a995e34c4bd61ca7bcbb449716251d0a","schema_version":"1.0","event_id":"sha256:c0c65c4e01256a86a0520b981e3448b9a995e34c4bd61ca7bcbb449716251d0a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/B36XH6FCU5ZO67FGBVVXBIKWZR/bundle.json","state_url":"https://pith.science/pith/B36XH6FCU5ZO67FGBVVXBIKWZR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/B36XH6FCU5ZO67FGBVVXBIKWZR/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":"2026-08-19T16:16:27Z","links":{"resolver":"https://pith.science/pith/B36XH6FCU5ZO67FGBVVXBIKWZR","bundle":"https://pith.science/pith/B36XH6FCU5ZO67FGBVVXBIKWZR/bundle.json","state":"https://pith.science/pith/B36XH6FCU5ZO67FGBVVXBIKWZR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/B36XH6FCU5ZO67FGBVVXBIKWZR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:B36XH6FCU5ZO67FGBVVXBIKWZR","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":"ed4353e84aca7ea1a1194b6f3198a61d15a8a40fe4566cdfbea655f4755e61dc","cross_cats_sorted":["cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-10T10:27:43Z","title_canon_sha256":"9620fd9b3733cc3684d4b72a1f8842b130d69f7f89ea3a167a0f8ce80884d080"},"schema_version":"1.0","source":{"id":"2504.07633","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.07633","created_at":"2026-07-05T11:20:52Z"},{"alias_kind":"arxiv_version","alias_value":"2504.07633v3","created_at":"2026-07-05T11:20:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.07633","created_at":"2026-07-05T11:20:52Z"},{"alias_kind":"pith_short_12","alias_value":"B36XH6FCU5ZO","created_at":"2026-07-05T11:20:52Z"},{"alias_kind":"pith_short_16","alias_value":"B36XH6FCU5ZO67FG","created_at":"2026-07-05T11:20:52Z"},{"alias_kind":"pith_short_8","alias_value":"B36XH6FC","created_at":"2026-07-05T11:20:52Z"}],"graph_snapshots":[{"event_id":"sha256:c0c65c4e01256a86a0520b981e3448b9a995e34c4bd61ca7bcbb449716251d0a","target":"graph","created_at":"2026-07-05T11:20:52Z","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/2504.07633/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Hebbian learning limits Hopfield network storage capacity (pattern-to-neuron ratio around 0.14). We propose Kernel Logistic Regression (KLR) learning. Unlike linear methods, KLR uses kernels to implicitly map patterns to high-dimensional feature space, enhancing separability. By learning dual variables, KLR dramatically improves storage capacity, achieving perfect recall even when pattern numbers exceed neuron numbers (up to ratio 1.5 shown), and enhances noise robustness. KLR demonstrably outperforms Hebbian and linear logistic regression approaches.","authors_text":"Akira Tamamori","cross_cats":["cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-10T10:27:43Z","title":"Kernel Logistic Regression Learning for High-Capacity Hopfield Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.07633","kind":"arxiv","version":3},"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":"sha256:75494c463eb7c59d0f49eef1373fc80b6097f458071824bdbef5a5c40f6653cb","target":"record","created_at":"2026-07-05T11:20:52Z","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":"ed4353e84aca7ea1a1194b6f3198a61d15a8a40fe4566cdfbea655f4755e61dc","cross_cats_sorted":["cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-10T10:27:43Z","title_canon_sha256":"9620fd9b3733cc3684d4b72a1f8842b130d69f7f89ea3a167a0f8ce80884d080"},"schema_version":"1.0","source":{"id":"2504.07633","kind":"arxiv","version":3}},"canonical_sha256":"0efd73f8a2a772ef7ca60d6b70a156cc4fa3626afb2cf8fa2bb62a00c00e702d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0efd73f8a2a772ef7ca60d6b70a156cc4fa3626afb2cf8fa2bb62a00c00e702d","first_computed_at":"2026-07-05T11:20:52.555179Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:20:52.555179Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6xiAxVLxDgDdxQXR05xKxDE0kEozOqUcSnG5lUNRFxRTnb2IB010hkie66hO9GROD+luXN75VAUji6gEDYoaDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:20:52.555790Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.07633","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:75494c463eb7c59d0f49eef1373fc80b6097f458071824bdbef5a5c40f6653cb","sha256:c0c65c4e01256a86a0520b981e3448b9a995e34c4bd61ca7bcbb449716251d0a"],"state_sha256":"5655eeb06f634c90a2255f7229dbfac57cdaafc0d35aefdb1987171b49c58e55"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sLvgpcx4CtAWSYdD5V90uJOkrn9QG7Atr+wkg3Q1bbkk/8Fsj44kSZymlWD0KI4I2oPif/tJrrudLG/eFjNTDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T16:16:27.801351Z","bundle_sha256":"340e1e755b78672a0049388ddaee96015aa16fb0b2e7b2848d4d38ba56ac1872"}}