{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:QG47Q6I56I2YQKKPI7WSQDJEOV","short_pith_number":"pith:QG47Q6I5","canonical_record":{"source":{"id":"1807.07540","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-07-19T17:12:48Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"feeac6c489fa92c90ee22ffb2c7390f3f14cc801f8b94a2e77d3d036578febc9","abstract_canon_sha256":"4c1a90f4701336945e87cc03f036d0b6df72ec617c2cc74cc2e1d5cfb828f62b"},"schema_version":"1.0"},"canonical_sha256":"81b9f8791df23588294f47ed280d24755e867d2afad5f92898a409942f66cfca","source":{"kind":"arxiv","id":"1807.07540","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.07540","created_at":"2026-07-05T00:55:26Z"},{"alias_kind":"arxiv_version","alias_value":"1807.07540v5","created_at":"2026-07-05T00:55:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.07540","created_at":"2026-07-05T00:55:26Z"},{"alias_kind":"pith_short_12","alias_value":"QG47Q6I56I2Y","created_at":"2026-07-05T00:55:26Z"},{"alias_kind":"pith_short_16","alias_value":"QG47Q6I56I2YQKKP","created_at":"2026-07-05T00:55:26Z"},{"alias_kind":"pith_short_8","alias_value":"QG47Q6I5","created_at":"2026-07-05T00:55:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:QG47Q6I56I2YQKKPI7WSQDJEOV","target":"record","payload":{"canonical_record":{"source":{"id":"1807.07540","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-07-19T17:12:48Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"feeac6c489fa92c90ee22ffb2c7390f3f14cc801f8b94a2e77d3d036578febc9","abstract_canon_sha256":"4c1a90f4701336945e87cc03f036d0b6df72ec617c2cc74cc2e1d5cfb828f62b"},"schema_version":"1.0"},"canonical_sha256":"81b9f8791df23588294f47ed280d24755e867d2afad5f92898a409942f66cfca","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:55:26.713179Z","signature_b64":"FPiEHvM+MDhlCRLvhyu2ohzly3hdpaaIcRU7C3GhxjklpHskRUa3GszuaVTX4p9FUGb50w0dvRB1CA3yfbUTCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81b9f8791df23588294f47ed280d24755e867d2afad5f92898a409942f66cfca","last_reissued_at":"2026-07-05T00:55:26.712760Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:55:26.712760Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1807.07540","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:55:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yqn/KOZvE5TqlZ1PFzZ7d1/OxCAZwQ6RAelXksblr7j3pg7zv4LY3uyRj7xdxQL6ZvVm+oDFgZlMUWhWJc6FAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T14:35:18.197381Z"},"content_sha256":"eca51e759d2c481bda8d96098296067c79f578a1fee567d236dd2b0375c9327c","schema_version":"1.0","event_id":"sha256:eca51e759d2c481bda8d96098296067c79f578a1fee567d236dd2b0375c9327c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:QG47Q6I56I2YQKKPI7WSQDJEOV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bayesian filtering unifies adaptive and non-adaptive neural network optimization methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Laurence Aitchison","submitted_at":"2018-07-19T17:12:48Z","abstract_excerpt":"We formulate the problem of neural network optimization as Bayesian filtering, where the observations are the backpropagated gradients. While neural network optimization has previously been studied using natural gradient methods which are closely related to Bayesian inference, they were unable to recover standard optimizers such as Adam and RMSprop with a root-mean-square gradient normalizer, instead getting a mean-square normalizer. To recover the root-mean-square normalizer, we find it necessary to account for the temporal dynamics of all the other parameters as they are geing optimized. The"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.07540","kind":"arxiv","version":5},"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/1807.07540/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":"2026-07-05T00:55:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i68I2Rk+Yy+RccCDFPnKslrd2/ikwdiId+V57TjL4acksxMSUWWdhqjabmRlLygDHooqyY/vZ2JYTgzYUNg9BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T14:35:18.197685Z"},"content_sha256":"d61485156726536ec8e57556b40ca0172c7be66f6b242faf3baace293ffe7852","schema_version":"1.0","event_id":"sha256:d61485156726536ec8e57556b40ca0172c7be66f6b242faf3baace293ffe7852"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QG47Q6I56I2YQKKPI7WSQDJEOV/bundle.json","state_url":"https://pith.science/pith/QG47Q6I56I2YQKKPI7WSQDJEOV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QG47Q6I56I2YQKKPI7WSQDJEOV/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":"2026-08-17T14:35:18Z","links":{"resolver":"https://pith.science/pith/QG47Q6I56I2YQKKPI7WSQDJEOV","bundle":"https://pith.science/pith/QG47Q6I56I2YQKKPI7WSQDJEOV/bundle.json","state":"https://pith.science/pith/QG47Q6I56I2YQKKPI7WSQDJEOV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QG47Q6I56I2YQKKPI7WSQDJEOV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:QG47Q6I56I2YQKKPI7WSQDJEOV","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":"4c1a90f4701336945e87cc03f036d0b6df72ec617c2cc74cc2e1d5cfb828f62b","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-07-19T17:12:48Z","title_canon_sha256":"feeac6c489fa92c90ee22ffb2c7390f3f14cc801f8b94a2e77d3d036578febc9"},"schema_version":"1.0","source":{"id":"1807.07540","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.07540","created_at":"2026-07-05T00:55:26Z"},{"alias_kind":"arxiv_version","alias_value":"1807.07540v5","created_at":"2026-07-05T00:55:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.07540","created_at":"2026-07-05T00:55:26Z"},{"alias_kind":"pith_short_12","alias_value":"QG47Q6I56I2Y","created_at":"2026-07-05T00:55:26Z"},{"alias_kind":"pith_short_16","alias_value":"QG47Q6I56I2YQKKP","created_at":"2026-07-05T00:55:26Z"},{"alias_kind":"pith_short_8","alias_value":"QG47Q6I5","created_at":"2026-07-05T00:55:26Z"}],"graph_snapshots":[{"event_id":"sha256:d61485156726536ec8e57556b40ca0172c7be66f6b242faf3baace293ffe7852","target":"graph","created_at":"2026-07-05T00:55:26Z","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/1807.07540/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We formulate the problem of neural network optimization as Bayesian filtering, where the observations are the backpropagated gradients. While neural network optimization has previously been studied using natural gradient methods which are closely related to Bayesian inference, they were unable to recover standard optimizers such as Adam and RMSprop with a root-mean-square gradient normalizer, instead getting a mean-square normalizer. To recover the root-mean-square normalizer, we find it necessary to account for the temporal dynamics of all the other parameters as they are geing optimized. The","authors_text":"Laurence Aitchison","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-07-19T17:12:48Z","title":"Bayesian filtering unifies adaptive and non-adaptive neural network optimization methods"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.07540","kind":"arxiv","version":5},"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:eca51e759d2c481bda8d96098296067c79f578a1fee567d236dd2b0375c9327c","target":"record","created_at":"2026-07-05T00:55:26Z","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":"4c1a90f4701336945e87cc03f036d0b6df72ec617c2cc74cc2e1d5cfb828f62b","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-07-19T17:12:48Z","title_canon_sha256":"feeac6c489fa92c90ee22ffb2c7390f3f14cc801f8b94a2e77d3d036578febc9"},"schema_version":"1.0","source":{"id":"1807.07540","kind":"arxiv","version":5}},"canonical_sha256":"81b9f8791df23588294f47ed280d24755e867d2afad5f92898a409942f66cfca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"81b9f8791df23588294f47ed280d24755e867d2afad5f92898a409942f66cfca","first_computed_at":"2026-07-05T00:55:26.712760Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:55:26.712760Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FPiEHvM+MDhlCRLvhyu2ohzly3hdpaaIcRU7C3GhxjklpHskRUa3GszuaVTX4p9FUGb50w0dvRB1CA3yfbUTCw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:55:26.713179Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.07540","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eca51e759d2c481bda8d96098296067c79f578a1fee567d236dd2b0375c9327c","sha256:d61485156726536ec8e57556b40ca0172c7be66f6b242faf3baace293ffe7852"],"state_sha256":"be77c1e4cd0ff47229b527ed98c2ce8ead92ce9a14e59826b5813fdd0ef18006"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NYe3Ik++rvxMbC3dQBJm1385JVNVLDSvn4wOiGpHUmv5BOlauZu3Ax23eD4SPWZxuSjDJFnVs2tfCXDLTdjIAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T14:35:18.200584Z","bundle_sha256":"761d0adcbb3b2bc58f539ec89584c03e5bd92cdca1810f11a4f3e2d797919031"}}