{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:PCTV5BEGNPRGQ5FODQUUBNCG5P","short_pith_number":"pith:PCTV5BEG","canonical_record":{"source":{"id":"2306.04815","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-07T22:37:11Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"f70b0ff80eac9a535b691dcd2f640796b58a41e0c555bc5bac9b47f1a145d9d1","abstract_canon_sha256":"650dc4e3b73f0c92ffab7c83be734882db1f68a764548f9e1a5b03c9cafbd977"},"schema_version":"1.0"},"canonical_sha256":"78a75e84866be26874ae1c2940b446ebfcab7ba116f4016016a470c4b6ccd56c","source":{"kind":"arxiv","id":"2306.04815","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.04815","created_at":"2026-07-05T08:28:01Z"},{"alias_kind":"arxiv_version","alias_value":"2306.04815v3","created_at":"2026-07-05T08:28:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.04815","created_at":"2026-07-05T08:28:01Z"},{"alias_kind":"pith_short_12","alias_value":"PCTV5BEGNPRG","created_at":"2026-07-05T08:28:01Z"},{"alias_kind":"pith_short_16","alias_value":"PCTV5BEGNPRGQ5FO","created_at":"2026-07-05T08:28:01Z"},{"alias_kind":"pith_short_8","alias_value":"PCTV5BEG","created_at":"2026-07-05T08:28:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:PCTV5BEGNPRGQ5FODQUUBNCG5P","target":"record","payload":{"canonical_record":{"source":{"id":"2306.04815","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-07T22:37:11Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"f70b0ff80eac9a535b691dcd2f640796b58a41e0c555bc5bac9b47f1a145d9d1","abstract_canon_sha256":"650dc4e3b73f0c92ffab7c83be734882db1f68a764548f9e1a5b03c9cafbd977"},"schema_version":"1.0"},"canonical_sha256":"78a75e84866be26874ae1c2940b446ebfcab7ba116f4016016a470c4b6ccd56c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:01.146615Z","signature_b64":"5lFyEEq/Q29TjevxAhtyWlle9dnp6xvwDQfWqF+wWbTO/lmaHfJ1h88c3qnj9Y7/oFlbh1qLD1DuxCuXec2xBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78a75e84866be26874ae1c2940b446ebfcab7ba116f4016016a470c4b6ccd56c","last_reissued_at":"2026-07-05T08:28:01.146191Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:01.146191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.04815","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":"2026-07-05T08:28:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DKR21H+1pVIXWIBmR/ZeeAc5drwyUFrrpXCYXkLfzN9+mvn0v2umXinZPypAYeA/+H0y2SBFgikUzdbbVf2nBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T09:22:41.980227Z"},"content_sha256":"e6c2470ec8df5bb144b318e330c8dfe92cdff6616ade7d4f5e23e87a8ae9c037","schema_version":"1.0","event_id":"sha256:e6c2470ec8df5bb144b318e330c8dfe92cdff6616ade7d4f5e23e87a8ae9c037"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:PCTV5BEGNPRGQ5FODQUUBNCG5P","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Catapults in SGD: spikes in the training loss and their impact on generalization through feature learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Adityanarayanan Radhakrishnan, Chaoyue Liu, Libin Zhu, Mikhail Belkin","submitted_at":"2023-06-07T22:37:11Z","abstract_excerpt":"In this paper, we first present an explanation regarding the common occurrence of spikes in the training loss when neural networks are trained with stochastic gradient descent (SGD). We provide evidence that the spikes in the training loss of SGD are \"catapults\", an optimization phenomenon originally observed in GD with large learning rates in [Lewkowycz et al. 2020]. We empirically show that these catapults occur in a low-dimensional subspace spanned by the top eigenvectors of the tangent kernel, for both GD and SGD. Second, we posit an explanation for how catapults lead to better generalizat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.04815","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2306.04815/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":"2026-07-05T08:28:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Is3SGxO4O9uPv1q8sPzp3bQ2gNqwHZP+i0uf5ed+Z9M2ezZXiKc0v0prhSWAa3oMZpvyRQL+N6+d7XckKhKjBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T09:22:41.980773Z"},"content_sha256":"ed88e9039550c7b91ab86ab67ee7e24432484aa6dc921e9f0a8f09da5438a82d","schema_version":"1.0","event_id":"sha256:ed88e9039550c7b91ab86ab67ee7e24432484aa6dc921e9f0a8f09da5438a82d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PCTV5BEGNPRGQ5FODQUUBNCG5P/bundle.json","state_url":"https://pith.science/pith/PCTV5BEGNPRGQ5FODQUUBNCG5P/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PCTV5BEGNPRGQ5FODQUUBNCG5P/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":"2026-08-07T09:22:41Z","links":{"resolver":"https://pith.science/pith/PCTV5BEGNPRGQ5FODQUUBNCG5P","bundle":"https://pith.science/pith/PCTV5BEGNPRGQ5FODQUUBNCG5P/bundle.json","state":"https://pith.science/pith/PCTV5BEGNPRGQ5FODQUUBNCG5P/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PCTV5BEGNPRGQ5FODQUUBNCG5P/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:PCTV5BEGNPRGQ5FODQUUBNCG5P","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":"650dc4e3b73f0c92ffab7c83be734882db1f68a764548f9e1a5b03c9cafbd977","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-07T22:37:11Z","title_canon_sha256":"f70b0ff80eac9a535b691dcd2f640796b58a41e0c555bc5bac9b47f1a145d9d1"},"schema_version":"1.0","source":{"id":"2306.04815","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.04815","created_at":"2026-07-05T08:28:01Z"},{"alias_kind":"arxiv_version","alias_value":"2306.04815v3","created_at":"2026-07-05T08:28:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.04815","created_at":"2026-07-05T08:28:01Z"},{"alias_kind":"pith_short_12","alias_value":"PCTV5BEGNPRG","created_at":"2026-07-05T08:28:01Z"},{"alias_kind":"pith_short_16","alias_value":"PCTV5BEGNPRGQ5FO","created_at":"2026-07-05T08:28:01Z"},{"alias_kind":"pith_short_8","alias_value":"PCTV5BEG","created_at":"2026-07-05T08:28:01Z"}],"graph_snapshots":[{"event_id":"sha256:ed88e9039550c7b91ab86ab67ee7e24432484aa6dc921e9f0a8f09da5438a82d","target":"graph","created_at":"2026-07-05T08:28:01Z","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/2306.04815/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we first present an explanation regarding the common occurrence of spikes in the training loss when neural networks are trained with stochastic gradient descent (SGD). We provide evidence that the spikes in the training loss of SGD are \"catapults\", an optimization phenomenon originally observed in GD with large learning rates in [Lewkowycz et al. 2020]. We empirically show that these catapults occur in a low-dimensional subspace spanned by the top eigenvectors of the tangent kernel, for both GD and SGD. Second, we posit an explanation for how catapults lead to better generalizat","authors_text":"Adityanarayanan Radhakrishnan, Chaoyue Liu, Libin Zhu, Mikhail Belkin","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-07T22:37:11Z","title":"Catapults in SGD: spikes in the training loss and their impact on generalization through feature learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.04815","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:e6c2470ec8df5bb144b318e330c8dfe92cdff6616ade7d4f5e23e87a8ae9c037","target":"record","created_at":"2026-07-05T08:28:01Z","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":"650dc4e3b73f0c92ffab7c83be734882db1f68a764548f9e1a5b03c9cafbd977","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-07T22:37:11Z","title_canon_sha256":"f70b0ff80eac9a535b691dcd2f640796b58a41e0c555bc5bac9b47f1a145d9d1"},"schema_version":"1.0","source":{"id":"2306.04815","kind":"arxiv","version":3}},"canonical_sha256":"78a75e84866be26874ae1c2940b446ebfcab7ba116f4016016a470c4b6ccd56c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"78a75e84866be26874ae1c2940b446ebfcab7ba116f4016016a470c4b6ccd56c","first_computed_at":"2026-07-05T08:28:01.146191Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:28:01.146191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5lFyEEq/Q29TjevxAhtyWlle9dnp6xvwDQfWqF+wWbTO/lmaHfJ1h88c3qnj9Y7/oFlbh1qLD1DuxCuXec2xBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:28:01.146615Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.04815","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e6c2470ec8df5bb144b318e330c8dfe92cdff6616ade7d4f5e23e87a8ae9c037","sha256:ed88e9039550c7b91ab86ab67ee7e24432484aa6dc921e9f0a8f09da5438a82d"],"state_sha256":"43d03d65f2272e9ae6bd4025a349ab73074a77ee23ca984403640f6b79f89e89"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mYT32Yvz80mcsDt5dKyCRlBUpnlap9T356g1hOzLEhPTRkZluUhBgEXKSqGqUQR0IwvOcoD6kNQaNuwAKtZLDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T09:22:41.990592Z","bundle_sha256":"00a812937d47ff42da1ff73c0324c6bbb751d072006a56e5f385d66452973561"}}