{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:FZVFMSKND7UKID5BII7XQMCBDB","short_pith_number":"pith:FZVFMSKN","canonical_record":{"source":{"id":"1712.09913","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-28T16:15:42Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"6bf95bbb7f33cc1bb51295c218f9a7172708c71d094645cf081a282651cad042","abstract_canon_sha256":"303541e3fa4f9b129acf43d75454eb48f11fb05199781456890d88f7261ecbcf"},"schema_version":"1.0"},"canonical_sha256":"2e6a56494d1fe8a40fa1423f783041187a1f590299749c46f58a4964c0b0576c","source":{"kind":"arxiv","id":"1712.09913","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.09913","created_at":"2026-05-18T00:01:23Z"},{"alias_kind":"arxiv_version","alias_value":"1712.09913v3","created_at":"2026-05-18T00:01:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.09913","created_at":"2026-05-18T00:01:23Z"},{"alias_kind":"pith_short_12","alias_value":"FZVFMSKND7UK","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_16","alias_value":"FZVFMSKND7UKID5B","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_8","alias_value":"FZVFMSKN","created_at":"2026-05-18T12:31:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:FZVFMSKND7UKID5BII7XQMCBDB","target":"record","payload":{"canonical_record":{"source":{"id":"1712.09913","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-28T16:15:42Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"6bf95bbb7f33cc1bb51295c218f9a7172708c71d094645cf081a282651cad042","abstract_canon_sha256":"303541e3fa4f9b129acf43d75454eb48f11fb05199781456890d88f7261ecbcf"},"schema_version":"1.0"},"canonical_sha256":"2e6a56494d1fe8a40fa1423f783041187a1f590299749c46f58a4964c0b0576c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:23.493047Z","signature_b64":"iDfuAGUaBptVEtc846Hul6Dbc4OikZr8YgpogF8lnNiPFVHL2wKbOI8tTMt5pHhkDCbGz6/BOarIZtHdcF+FBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e6a56494d1fe8a40fa1423f783041187a1f590299749c46f58a4964c0b0576c","last_reissued_at":"2026-05-18T00:01:23.492664Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:23.492664Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1712.09913","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":"2026-05-18T00:01:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dbBuOeOlOxNSnS9S5T86i92DQcZzbnEWpuEo3/2xBi7aZg8s+voz9aX65nCJssYzTPSr4rM8ZsSpdGs67veBCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T03:53:33.325802Z"},"content_sha256":"751a6f1c3b1488544b736b15a1c39958e4919932fd303c665de8a7423aa7c210","schema_version":"1.0","event_id":"sha256:751a6f1c3b1488544b736b15a1c39958e4919932fd303c665de8a7423aa7c210"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:FZVFMSKND7UKID5BII7XQMCBDB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Visualizing the Loss Landscape of Neural Nets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Christoph Studer, Gavin Taylor, Hao Li, Tom Goldstein, Zheng Xu","submitted_at":"2017-12-28T16:15:42Z","abstract_excerpt":"Neural network training relies on our ability to find \"good\" minimizers of highly non-convex loss functions. It is well-known that certain network architecture designs (e.g., skip connections) produce loss functions that train easier, and well-chosen training parameters (batch size, learning rate, optimizer) produce minimizers that generalize better. However, the reasons for these differences, and their effects on the underlying loss landscape, are not well understood. In this paper, we explore the structure of neural loss functions, and the effect of loss landscapes on generalization, using a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.09913","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":""},"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":"2026-05-18T00:01:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5Ph0uGTFZvv87ZWjjSnqx+WGB2Yhf0sFkifpE1enACU56hWRecujiiKUFYLFjCvU1fynYp3lfYCCqONNsJ4oBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T03:53:33.326398Z"},"content_sha256":"1145a00b48be7d8c7bb0e5e33ab85b638ed0f712da6ab7e5cc0432f07ac186dc","schema_version":"1.0","event_id":"sha256:1145a00b48be7d8c7bb0e5e33ab85b638ed0f712da6ab7e5cc0432f07ac186dc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FZVFMSKND7UKID5BII7XQMCBDB/bundle.json","state_url":"https://pith.science/pith/FZVFMSKND7UKID5BII7XQMCBDB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FZVFMSKND7UKID5BII7XQMCBDB/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":"2026-05-27T03:53:33Z","links":{"resolver":"https://pith.science/pith/FZVFMSKND7UKID5BII7XQMCBDB","bundle":"https://pith.science/pith/FZVFMSKND7UKID5BII7XQMCBDB/bundle.json","state":"https://pith.science/pith/FZVFMSKND7UKID5BII7XQMCBDB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FZVFMSKND7UKID5BII7XQMCBDB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:FZVFMSKND7UKID5BII7XQMCBDB","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":"303541e3fa4f9b129acf43d75454eb48f11fb05199781456890d88f7261ecbcf","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-28T16:15:42Z","title_canon_sha256":"6bf95bbb7f33cc1bb51295c218f9a7172708c71d094645cf081a282651cad042"},"schema_version":"1.0","source":{"id":"1712.09913","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.09913","created_at":"2026-05-18T00:01:23Z"},{"alias_kind":"arxiv_version","alias_value":"1712.09913v3","created_at":"2026-05-18T00:01:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.09913","created_at":"2026-05-18T00:01:23Z"},{"alias_kind":"pith_short_12","alias_value":"FZVFMSKND7UK","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_16","alias_value":"FZVFMSKND7UKID5B","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_8","alias_value":"FZVFMSKN","created_at":"2026-05-18T12:31:15Z"}],"graph_snapshots":[{"event_id":"sha256:1145a00b48be7d8c7bb0e5e33ab85b638ed0f712da6ab7e5cc0432f07ac186dc","target":"graph","created_at":"2026-05-18T00:01:23Z","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":"Neural network training relies on our ability to find \"good\" minimizers of highly non-convex loss functions. It is well-known that certain network architecture designs (e.g., skip connections) produce loss functions that train easier, and well-chosen training parameters (batch size, learning rate, optimizer) produce minimizers that generalize better. However, the reasons for these differences, and their effects on the underlying loss landscape, are not well understood. In this paper, we explore the structure of neural loss functions, and the effect of loss landscapes on generalization, using a","authors_text":"Christoph Studer, Gavin Taylor, Hao Li, Tom Goldstein, Zheng Xu","cross_cats":["cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-28T16:15:42Z","title":"Visualizing the Loss Landscape of Neural Nets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.09913","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":"sha256:751a6f1c3b1488544b736b15a1c39958e4919932fd303c665de8a7423aa7c210","target":"record","created_at":"2026-05-18T00:01:23Z","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":"303541e3fa4f9b129acf43d75454eb48f11fb05199781456890d88f7261ecbcf","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-28T16:15:42Z","title_canon_sha256":"6bf95bbb7f33cc1bb51295c218f9a7172708c71d094645cf081a282651cad042"},"schema_version":"1.0","source":{"id":"1712.09913","kind":"arxiv","version":3}},"canonical_sha256":"2e6a56494d1fe8a40fa1423f783041187a1f590299749c46f58a4964c0b0576c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2e6a56494d1fe8a40fa1423f783041187a1f590299749c46f58a4964c0b0576c","first_computed_at":"2026-05-18T00:01:23.492664Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:01:23.492664Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iDfuAGUaBptVEtc846Hul6Dbc4OikZr8YgpogF8lnNiPFVHL2wKbOI8tTMt5pHhkDCbGz6/BOarIZtHdcF+FBg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:01:23.493047Z","signed_message":"canonical_sha256_bytes"},"source_id":"1712.09913","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:751a6f1c3b1488544b736b15a1c39958e4919932fd303c665de8a7423aa7c210","sha256:1145a00b48be7d8c7bb0e5e33ab85b638ed0f712da6ab7e5cc0432f07ac186dc"],"state_sha256":"42171281d834ce5cdd32dcdad89742c81591f6cef4d2a1622cfbbd0caed81428"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G+ix8gb4jIwMX8dsDxDmllrAw141k4re2YWRaDSaHD+rnqKxnjNeNBlK1CghDQqnV5Lp1R2aEq4VY8lvnDx8Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T03:53:33.329409Z","bundle_sha256":"a3859fc47e2f85c283fa9e070cf9a20cf85de58cfc937d404c3577b797fccbc8"}}