{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:MNEBOA6QWUYMQ5EFXAADXVEH3E","short_pith_number":"pith:MNEBOA6Q","canonical_record":{"source":{"id":"1803.09119","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-03-24T14:22:36Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"16b2bed8ba69128dcb370b6ff0f82bb899a7ed1a16fb513914b9fc2ab4e9647f","abstract_canon_sha256":"08e3b8bd5fa47004a961331a1495706f8ce32a7e77107523c26c93cd493827dc"},"schema_version":"1.0"},"canonical_sha256":"63481703d0b530c87485b8003bd487d919577b2f5ccf4d5cd964107cb7904c3d","source":{"kind":"arxiv","id":"1803.09119","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.09119","created_at":"2026-05-18T00:20:12Z"},{"alias_kind":"arxiv_version","alias_value":"1803.09119v1","created_at":"2026-05-18T00:20:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.09119","created_at":"2026-05-18T00:20:12Z"},{"alias_kind":"pith_short_12","alias_value":"MNEBOA6QWUYM","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"MNEBOA6QWUYMQ5EF","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"MNEBOA6Q","created_at":"2026-05-18T12:32:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:MNEBOA6QWUYMQ5EFXAADXVEH3E","target":"record","payload":{"canonical_record":{"source":{"id":"1803.09119","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-03-24T14:22:36Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"16b2bed8ba69128dcb370b6ff0f82bb899a7ed1a16fb513914b9fc2ab4e9647f","abstract_canon_sha256":"08e3b8bd5fa47004a961331a1495706f8ce32a7e77107523c26c93cd493827dc"},"schema_version":"1.0"},"canonical_sha256":"63481703d0b530c87485b8003bd487d919577b2f5ccf4d5cd964107cb7904c3d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:20:12.571707Z","signature_b64":"79lA01pbp4d0aXaH7Kt2BTzxQokA8V22Acg+dSnXj8gsozrCi6RWMVJ+mCltlfWBcC2Elk3vN5S6myBp8rPzBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"63481703d0b530c87485b8003bd487d919577b2f5ccf4d5cd964107cb7904c3d","last_reissued_at":"2026-05-18T00:20:12.571253Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:20:12.571253Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1803.09119","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":"2026-05-18T00:20:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cHRSIqgOVX6wIBOFnmVheAj+xx//KD0Mdaa9x3jh+ot+HhGy7CmIHhDn3oLYp3+qjbWtitzrOtE2thOriGwrCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T18:11:02.941549Z"},"content_sha256":"3e4cededd2430009811d54ddb45cecebbcba2b354e448115faaef4f4db154d89","schema_version":"1.0","event_id":"sha256:3e4cededd2430009811d54ddb45cecebbcba2b354e448115faaef4f4db154d89"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:MNEBOA6QWUYMQ5EFXAADXVEH3E","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Gradient descent in Gaussian random fields as a toy model for high-dimensional optimisation in deep learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Mariano Chouza, Stefan Zohren, Stephen Roberts","submitted_at":"2018-03-24T14:22:36Z","abstract_excerpt":"In this paper we model the loss function of high-dimensional optimization problems by a Gaussian random field, or equivalently a Gaussian process. Our aim is to study gradient descent in such loss functions or energy landscapes and compare it to results obtained from real high-dimensional optimization problems such as encountered in deep learning. In particular, we analyze the distribution of the improved loss function after a step of gradient descent, provide analytic expressions for the moments as well as prove asymptotic normality as the dimension of the parameter space becomes large. Moreo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.09119","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":""},"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":"2026-05-18T00:20:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SXcV8PkxbyzO7jDHShqI8lVYPlOM/DWIEmgFkmQRHF1wLZin977+YfCHCWbODfdkdGJ2UMrcL0HO+2R6NrJDAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T18:11:02.942249Z"},"content_sha256":"4ebae77be4fda679ef5e554086ff523c666d4940ffc10cab809198a436d40e23","schema_version":"1.0","event_id":"sha256:4ebae77be4fda679ef5e554086ff523c666d4940ffc10cab809198a436d40e23"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MNEBOA6QWUYMQ5EFXAADXVEH3E/bundle.json","state_url":"https://pith.science/pith/MNEBOA6QWUYMQ5EFXAADXVEH3E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MNEBOA6QWUYMQ5EFXAADXVEH3E/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":"2026-06-08T18:11:02Z","links":{"resolver":"https://pith.science/pith/MNEBOA6QWUYMQ5EFXAADXVEH3E","bundle":"https://pith.science/pith/MNEBOA6QWUYMQ5EFXAADXVEH3E/bundle.json","state":"https://pith.science/pith/MNEBOA6QWUYMQ5EFXAADXVEH3E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MNEBOA6QWUYMQ5EFXAADXVEH3E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:MNEBOA6QWUYMQ5EFXAADXVEH3E","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":"08e3b8bd5fa47004a961331a1495706f8ce32a7e77107523c26c93cd493827dc","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-03-24T14:22:36Z","title_canon_sha256":"16b2bed8ba69128dcb370b6ff0f82bb899a7ed1a16fb513914b9fc2ab4e9647f"},"schema_version":"1.0","source":{"id":"1803.09119","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.09119","created_at":"2026-05-18T00:20:12Z"},{"alias_kind":"arxiv_version","alias_value":"1803.09119v1","created_at":"2026-05-18T00:20:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.09119","created_at":"2026-05-18T00:20:12Z"},{"alias_kind":"pith_short_12","alias_value":"MNEBOA6QWUYM","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"MNEBOA6QWUYMQ5EF","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"MNEBOA6Q","created_at":"2026-05-18T12:32:37Z"}],"graph_snapshots":[{"event_id":"sha256:4ebae77be4fda679ef5e554086ff523c666d4940ffc10cab809198a436d40e23","target":"graph","created_at":"2026-05-18T00:20:12Z","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":"In this paper we model the loss function of high-dimensional optimization problems by a Gaussian random field, or equivalently a Gaussian process. Our aim is to study gradient descent in such loss functions or energy landscapes and compare it to results obtained from real high-dimensional optimization problems such as encountered in deep learning. In particular, we analyze the distribution of the improved loss function after a step of gradient descent, provide analytic expressions for the moments as well as prove asymptotic normality as the dimension of the parameter space becomes large. Moreo","authors_text":"Mariano Chouza, Stefan Zohren, Stephen Roberts","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-03-24T14:22:36Z","title":"Gradient descent in Gaussian random fields as a toy model for high-dimensional optimisation in deep learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.09119","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":"sha256:3e4cededd2430009811d54ddb45cecebbcba2b354e448115faaef4f4db154d89","target":"record","created_at":"2026-05-18T00:20:12Z","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":"08e3b8bd5fa47004a961331a1495706f8ce32a7e77107523c26c93cd493827dc","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-03-24T14:22:36Z","title_canon_sha256":"16b2bed8ba69128dcb370b6ff0f82bb899a7ed1a16fb513914b9fc2ab4e9647f"},"schema_version":"1.0","source":{"id":"1803.09119","kind":"arxiv","version":1}},"canonical_sha256":"63481703d0b530c87485b8003bd487d919577b2f5ccf4d5cd964107cb7904c3d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"63481703d0b530c87485b8003bd487d919577b2f5ccf4d5cd964107cb7904c3d","first_computed_at":"2026-05-18T00:20:12.571253Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:20:12.571253Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"79lA01pbp4d0aXaH7Kt2BTzxQokA8V22Acg+dSnXj8gsozrCi6RWMVJ+mCltlfWBcC2Elk3vN5S6myBp8rPzBA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:20:12.571707Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.09119","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3e4cededd2430009811d54ddb45cecebbcba2b354e448115faaef4f4db154d89","sha256:4ebae77be4fda679ef5e554086ff523c666d4940ffc10cab809198a436d40e23"],"state_sha256":"90f21e89f159d8e4ce6c47dd1095983428463da984aa4158f53062ee6310cbdf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e9ZWbFODgPu/q+9mrYp932knVdSjWSASmX8iyca4nP0cnpso+Z6Jd7jxoZAeKmpbYUc4rLuXgHTQ0+q0xNd8Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T18:11:02.946330Z","bundle_sha256":"036c88af704bab627c5132992395183b8482ead23e8aedb25b927604de9e593e"}}