{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:JRHQVXPAOOAQHH2RB4JYUKOZXL","short_pith_number":"pith:JRHQVXPA","canonical_record":{"source":{"id":"1906.04724","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-11T17:54:47Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"473709d4af709410b9db520ab49703e06bfcbb965206d7037dc84d40ab4b81b5","abstract_canon_sha256":"f3834a8dcfda7fb0b68b35c329aff3fc9ee58b6150dafbaf5f4336dd240fe12d"},"schema_version":"1.0"},"canonical_sha256":"4c4f0adde07381039f510f138a29d9badc90aeb5254dea4b384bac043668d2e7","source":{"kind":"arxiv","id":"1906.04724","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.04724","created_at":"2026-05-17T23:43:33Z"},{"alias_kind":"arxiv_version","alias_value":"1906.04724v1","created_at":"2026-05-17T23:43:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.04724","created_at":"2026-05-17T23:43:33Z"},{"alias_kind":"pith_short_12","alias_value":"JRHQVXPAOOAQ","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"JRHQVXPAOOAQHH2R","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"JRHQVXPA","created_at":"2026-05-18T12:33:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:JRHQVXPAOOAQHH2RB4JYUKOZXL","target":"record","payload":{"canonical_record":{"source":{"id":"1906.04724","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-11T17:54:47Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"473709d4af709410b9db520ab49703e06bfcbb965206d7037dc84d40ab4b81b5","abstract_canon_sha256":"f3834a8dcfda7fb0b68b35c329aff3fc9ee58b6150dafbaf5f4336dd240fe12d"},"schema_version":"1.0"},"canonical_sha256":"4c4f0adde07381039f510f138a29d9badc90aeb5254dea4b384bac043668d2e7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:33.688300Z","signature_b64":"FzaPx7pYKe8O+6nq8KlAtKvN9dj/wQFTScAMu3LocHATGUuOLKvezu3fZZMwHnd3ozpAHQYWHG27fiPhDtPrCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c4f0adde07381039f510f138a29d9badc90aeb5254dea4b384bac043668d2e7","last_reissued_at":"2026-05-17T23:43:33.687943Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:33.687943Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.04724","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":"2026-05-17T23:43:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Cft8m1L+Ta9VaIDZjpFBs+qReGOirVnkdWk9CkQ2YNPNYucNKWb57ndZFaJ1B6jG75ngT7L4aSYMNqQefiNPBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T06:20:49.041100Z"},"content_sha256":"30edbfdbf7fff7a3f743c872559588814ba1ad938a40905df5de6c02f66523c7","schema_version":"1.0","event_id":"sha256:30edbfdbf7fff7a3f743c872559588814ba1ad938a40905df5de6c02f66523c7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:JRHQVXPAOOAQHH2RB4JYUKOZXL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Large Scale Structure of Neural Network Loss Landscapes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Stanislav Fort, Stanislaw Jastrzebski","submitted_at":"2019-06-11T17:54:47Z","abstract_excerpt":"There are many surprising and perhaps counter-intuitive properties of optimization of deep neural networks. We propose and experimentally verify a unified phenomenological model of the loss landscape that incorporates many of them. High dimensionality plays a key role in our model. Our core idea is to model the loss landscape as a set of high dimensional \\emph{wedges} that together form a large-scale, inter-connected structure and towards which optimization is drawn. We first show that hyperparameter choices such as learning rate, network width and $L_2$ regularization, affect the path optimiz"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.04724","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":"2026-05-17T23:43:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Vh9tjJZKms5Mh13JNZfN031am4B+tD66duB+yZEtHkDqz7J5GTwCq1VMZ3G5jl5UrhGEYV+NbFA0jHNX1NloCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T06:20:49.041860Z"},"content_sha256":"27d6cdec23206fb31dc2eb4eac0371dc1b484dab752926493cb7327d1a8ec571","schema_version":"1.0","event_id":"sha256:27d6cdec23206fb31dc2eb4eac0371dc1b484dab752926493cb7327d1a8ec571"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JRHQVXPAOOAQHH2RB4JYUKOZXL/bundle.json","state_url":"https://pith.science/pith/JRHQVXPAOOAQHH2RB4JYUKOZXL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JRHQVXPAOOAQHH2RB4JYUKOZXL/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":"2026-05-31T06:20:49Z","links":{"resolver":"https://pith.science/pith/JRHQVXPAOOAQHH2RB4JYUKOZXL","bundle":"https://pith.science/pith/JRHQVXPAOOAQHH2RB4JYUKOZXL/bundle.json","state":"https://pith.science/pith/JRHQVXPAOOAQHH2RB4JYUKOZXL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JRHQVXPAOOAQHH2RB4JYUKOZXL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:JRHQVXPAOOAQHH2RB4JYUKOZXL","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":"f3834a8dcfda7fb0b68b35c329aff3fc9ee58b6150dafbaf5f4336dd240fe12d","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-11T17:54:47Z","title_canon_sha256":"473709d4af709410b9db520ab49703e06bfcbb965206d7037dc84d40ab4b81b5"},"schema_version":"1.0","source":{"id":"1906.04724","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.04724","created_at":"2026-05-17T23:43:33Z"},{"alias_kind":"arxiv_version","alias_value":"1906.04724v1","created_at":"2026-05-17T23:43:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.04724","created_at":"2026-05-17T23:43:33Z"},{"alias_kind":"pith_short_12","alias_value":"JRHQVXPAOOAQ","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"JRHQVXPAOOAQHH2R","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"JRHQVXPA","created_at":"2026-05-18T12:33:21Z"}],"graph_snapshots":[{"event_id":"sha256:27d6cdec23206fb31dc2eb4eac0371dc1b484dab752926493cb7327d1a8ec571","target":"graph","created_at":"2026-05-17T23:43:33Z","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":"There are many surprising and perhaps counter-intuitive properties of optimization of deep neural networks. We propose and experimentally verify a unified phenomenological model of the loss landscape that incorporates many of them. High dimensionality plays a key role in our model. Our core idea is to model the loss landscape as a set of high dimensional \\emph{wedges} that together form a large-scale, inter-connected structure and towards which optimization is drawn. We first show that hyperparameter choices such as learning rate, network width and $L_2$ regularization, affect the path optimiz","authors_text":"Stanislav Fort, Stanislaw Jastrzebski","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-11T17:54:47Z","title":"Large Scale Structure of Neural Network Loss Landscapes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.04724","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":"sha256:30edbfdbf7fff7a3f743c872559588814ba1ad938a40905df5de6c02f66523c7","target":"record","created_at":"2026-05-17T23:43:33Z","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":"f3834a8dcfda7fb0b68b35c329aff3fc9ee58b6150dafbaf5f4336dd240fe12d","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-11T17:54:47Z","title_canon_sha256":"473709d4af709410b9db520ab49703e06bfcbb965206d7037dc84d40ab4b81b5"},"schema_version":"1.0","source":{"id":"1906.04724","kind":"arxiv","version":1}},"canonical_sha256":"4c4f0adde07381039f510f138a29d9badc90aeb5254dea4b384bac043668d2e7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4c4f0adde07381039f510f138a29d9badc90aeb5254dea4b384bac043668d2e7","first_computed_at":"2026-05-17T23:43:33.687943Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:43:33.687943Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FzaPx7pYKe8O+6nq8KlAtKvN9dj/wQFTScAMu3LocHATGUuOLKvezu3fZZMwHnd3ozpAHQYWHG27fiPhDtPrCg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:43:33.688300Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.04724","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:30edbfdbf7fff7a3f743c872559588814ba1ad938a40905df5de6c02f66523c7","sha256:27d6cdec23206fb31dc2eb4eac0371dc1b484dab752926493cb7327d1a8ec571"],"state_sha256":"821f91849d0a97b0228df76fc0a7e3ee88266abb64a913fb7ca95d936779ae5b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G56UnkKjuyveUSy63NadkEprJ/u7i46JQPbQx7grdsXtF5JJvUihmxLBe3/Y+Yj5N329UgE6xkRo7iuieglNAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T06:20:49.045357Z","bundle_sha256":"d794ae6679b7329a8664c56dda930d751d58e2e8e176762040219eff947c6f12"}}