{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:6VAEWOCQVHDPNWY6NFC2LKR4CP","short_pith_number":"pith:6VAEWOCQ","canonical_record":{"source":{"id":"1804.05965","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-04-16T22:43:41Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a3521b9895e5d6b689b8306fd4baf0c54a30620075b5bc62d4642914e28df250","abstract_canon_sha256":"20880c949590cf59497d55d7c75e8012c24033d17a69a0af0abe2a2ff4be9f0e"},"schema_version":"1.0"},"canonical_sha256":"f5404b3850a9c6f6db1e6945a5aa3c13db79c41e528e862067be383614a309be","source":{"kind":"arxiv","id":"1804.05965","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.05965","created_at":"2026-05-18T00:11:56Z"},{"alias_kind":"arxiv_version","alias_value":"1804.05965v2","created_at":"2026-05-18T00:11:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.05965","created_at":"2026-05-18T00:11:56Z"},{"alias_kind":"pith_short_12","alias_value":"6VAEWOCQVHDP","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"6VAEWOCQVHDPNWY6","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"6VAEWOCQ","created_at":"2026-05-18T12:32:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:6VAEWOCQVHDPNWY6NFC2LKR4CP","target":"record","payload":{"canonical_record":{"source":{"id":"1804.05965","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-04-16T22:43:41Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a3521b9895e5d6b689b8306fd4baf0c54a30620075b5bc62d4642914e28df250","abstract_canon_sha256":"20880c949590cf59497d55d7c75e8012c24033d17a69a0af0abe2a2ff4be9f0e"},"schema_version":"1.0"},"canonical_sha256":"f5404b3850a9c6f6db1e6945a5aa3c13db79c41e528e862067be383614a309be","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:11:56.977287Z","signature_b64":"X9HXkKkxR0DoolAq5C8lmeqFTM9vpik1a5EFqXdt2Lb3ORIsGg/aY9gnVczD9lOS//+IFcz3SZrDql1zZBf5BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5404b3850a9c6f6db1e6945a5aa3c13db79c41e528e862067be383614a309be","last_reissued_at":"2026-05-18T00:11:56.976761Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:11:56.976761Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1804.05965","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:11:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9l01QF/LXbJKWga9eU6vosCv7jp0Rpl/2ZcU0vDMd5pJzgI2mRUYJvBCuaT+j0X5hXvRH+p5bHUvOqb6u95PCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T22:23:19.146823Z"},"content_sha256":"ef340aa3845210af95c8a7712346b81c4cf3baf67f17776f3510e2eeba4648ae","schema_version":"1.0","event_id":"sha256:ef340aa3845210af95c8a7712346b81c4cf3baf67f17776f3510e2eeba4648ae"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:6VAEWOCQVHDPNWY6NFC2LKR4CP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MaxGain: Regularisation of Neural Networks by Constraining Activation Magnitudes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Bernhard Pfahringer, Eibe Frank, Henry Gouk, Michael Cree","submitted_at":"2018-04-16T22:43:41Z","abstract_excerpt":"Effective regularisation of neural networks is essential to combat overfitting due to the large number of parameters involved. We present an empirical analogue to the Lipschitz constant of a feed-forward neural network, which we refer to as the maximum gain. We hypothesise that constraining the gain of a network will have a regularising effect, similar to how constraining the Lipschitz constant of a network has been shown to improve generalisation. A simple algorithm is provided that involves rescaling the weight matrix of each layer after each parameter update. We conduct a series of studies "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.05965","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":""},"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":"2026-05-18T00:11:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vicxOUaL322nkKGql0DwlmIgyVmuqYaThurD6Eg8pZ7EnsjO2h6GUgS8G1w0u78/8G+BYeFrXopfGLSML7a5Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T22:23:19.147383Z"},"content_sha256":"748f1cf98f25fc7da7ca12c2b665e0636ecf071924017c3482ef684faf0c8667","schema_version":"1.0","event_id":"sha256:748f1cf98f25fc7da7ca12c2b665e0636ecf071924017c3482ef684faf0c8667"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6VAEWOCQVHDPNWY6NFC2LKR4CP/bundle.json","state_url":"https://pith.science/pith/6VAEWOCQVHDPNWY6NFC2LKR4CP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6VAEWOCQVHDPNWY6NFC2LKR4CP/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":"2026-06-01T22:23:19Z","links":{"resolver":"https://pith.science/pith/6VAEWOCQVHDPNWY6NFC2LKR4CP","bundle":"https://pith.science/pith/6VAEWOCQVHDPNWY6NFC2LKR4CP/bundle.json","state":"https://pith.science/pith/6VAEWOCQVHDPNWY6NFC2LKR4CP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6VAEWOCQVHDPNWY6NFC2LKR4CP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:6VAEWOCQVHDPNWY6NFC2LKR4CP","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":"20880c949590cf59497d55d7c75e8012c24033d17a69a0af0abe2a2ff4be9f0e","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-04-16T22:43:41Z","title_canon_sha256":"a3521b9895e5d6b689b8306fd4baf0c54a30620075b5bc62d4642914e28df250"},"schema_version":"1.0","source":{"id":"1804.05965","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.05965","created_at":"2026-05-18T00:11:56Z"},{"alias_kind":"arxiv_version","alias_value":"1804.05965v2","created_at":"2026-05-18T00:11:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.05965","created_at":"2026-05-18T00:11:56Z"},{"alias_kind":"pith_short_12","alias_value":"6VAEWOCQVHDP","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"6VAEWOCQVHDPNWY6","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"6VAEWOCQ","created_at":"2026-05-18T12:32:11Z"}],"graph_snapshots":[{"event_id":"sha256:748f1cf98f25fc7da7ca12c2b665e0636ecf071924017c3482ef684faf0c8667","target":"graph","created_at":"2026-05-18T00:11:56Z","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"},"paper":{"abstract_excerpt":"Effective regularisation of neural networks is essential to combat overfitting due to the large number of parameters involved. We present an empirical analogue to the Lipschitz constant of a feed-forward neural network, which we refer to as the maximum gain. We hypothesise that constraining the gain of a network will have a regularising effect, similar to how constraining the Lipschitz constant of a network has been shown to improve generalisation. A simple algorithm is provided that involves rescaling the weight matrix of each layer after each parameter update. We conduct a series of studies ","authors_text":"Bernhard Pfahringer, Eibe Frank, Henry Gouk, Michael Cree","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-04-16T22:43:41Z","title":"MaxGain: Regularisation of Neural Networks by Constraining Activation Magnitudes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.05965","kind":"arxiv","version":2},"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:ef340aa3845210af95c8a7712346b81c4cf3baf67f17776f3510e2eeba4648ae","target":"record","created_at":"2026-05-18T00:11:56Z","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":"20880c949590cf59497d55d7c75e8012c24033d17a69a0af0abe2a2ff4be9f0e","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-04-16T22:43:41Z","title_canon_sha256":"a3521b9895e5d6b689b8306fd4baf0c54a30620075b5bc62d4642914e28df250"},"schema_version":"1.0","source":{"id":"1804.05965","kind":"arxiv","version":2}},"canonical_sha256":"f5404b3850a9c6f6db1e6945a5aa3c13db79c41e528e862067be383614a309be","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f5404b3850a9c6f6db1e6945a5aa3c13db79c41e528e862067be383614a309be","first_computed_at":"2026-05-18T00:11:56.976761Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:11:56.976761Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"X9HXkKkxR0DoolAq5C8lmeqFTM9vpik1a5EFqXdt2Lb3ORIsGg/aY9gnVczD9lOS//+IFcz3SZrDql1zZBf5BA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:11:56.977287Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.05965","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ef340aa3845210af95c8a7712346b81c4cf3baf67f17776f3510e2eeba4648ae","sha256:748f1cf98f25fc7da7ca12c2b665e0636ecf071924017c3482ef684faf0c8667"],"state_sha256":"8bb6e1690d80a275b0908a0114f899d86365b36d1cf5e9e718dc89b9737ceeee"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TmWFpE6/PpD13T5+pLrje4Wfj+7jotwQbwQNJ3r+NewB6k0dGgRbTje/0lGotbvrGymer5RJXCtThaLXdk7XBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T22:23:19.150407Z","bundle_sha256":"eed5602d8acc834359b7b1f7fdf98a0cf45cf294bb73e314cba227729367030d"}}