{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:5SKNTGLAAFPG7V3TF33DF2HSWA","short_pith_number":"pith:5SKNTGLA","canonical_record":{"source":{"id":"1712.06559","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-18T18:10:39Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a30c6b5036366e79f924ca2915ea174e45ab2b11ad959743316f8e9354ab9a0d","abstract_canon_sha256":"138352b1eda421432d5481548296f5542c8a8fc12f12932df74da3b1ae55ac74"},"schema_version":"1.0"},"canonical_sha256":"ec94d99960015e6fd7732ef632e8f2b0376ad761a794790a82e120201dcdea4c","source":{"kind":"arxiv","id":"1712.06559","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.06559","created_at":"2026-05-18T00:13:10Z"},{"alias_kind":"arxiv_version","alias_value":"1712.06559v3","created_at":"2026-05-18T00:13:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.06559","created_at":"2026-05-18T00:13:10Z"},{"alias_kind":"pith_short_12","alias_value":"5SKNTGLAAFPG","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"5SKNTGLAAFPG7V3T","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"5SKNTGLA","created_at":"2026-05-18T12:31:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:5SKNTGLAAFPG7V3TF33DF2HSWA","target":"record","payload":{"canonical_record":{"source":{"id":"1712.06559","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-18T18:10:39Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a30c6b5036366e79f924ca2915ea174e45ab2b11ad959743316f8e9354ab9a0d","abstract_canon_sha256":"138352b1eda421432d5481548296f5542c8a8fc12f12932df74da3b1ae55ac74"},"schema_version":"1.0"},"canonical_sha256":"ec94d99960015e6fd7732ef632e8f2b0376ad761a794790a82e120201dcdea4c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:13:10.648646Z","signature_b64":"M6uuEe5og+pq3d9fmdLffQktD8l486lx1Gdu5xuSkGzdhMPwSMxPlMF+ntiqBIRXlKZ31KDJ2O5fq0+sID8KDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec94d99960015e6fd7732ef632e8f2b0376ad761a794790a82e120201dcdea4c","last_reissued_at":"2026-05-18T00:13:10.647994Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:13:10.647994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1712.06559","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":"2026-05-18T00:13:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7muvNxiGg0+GCshrOLqUXZFveJRvS6aD5u6MxGh6WpdY39tjRR9WKPGmEsjbyNZ9ZX1kKyStpmzFyNwnNJpEBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T14:57:45.803110Z"},"content_sha256":"0d2f51fd61e68245f448df08f8964bd702373fb50ab83da708bc519a8f9262bc","schema_version":"1.0","event_id":"sha256:0d2f51fd61e68245f448df08f8964bd702373fb50ab83da708bc519a8f9262bc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:5SKNTGLAAFPG7V3TF33DF2HSWA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Power of Interpolation: Understanding the Effectiveness of SGD in Modern Over-parametrized Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Mikhail Belkin, Raef Bassily, Siyuan Ma","submitted_at":"2017-12-18T18:10:39Z","abstract_excerpt":"In this paper we aim to formally explain the phenomenon of fast convergence of SGD observed in modern machine learning. The key observation is that most modern learning architectures are over-parametrized and are trained to interpolate the data by driving the empirical loss (classification and regression) close to zero. While it is still unclear why these interpolated solutions perform well on test data, we show that these regimes allow for fast convergence of SGD, comparable in number of iterations to full gradient descent.\n  For convex loss functions we obtain an exponential convergence boun"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.06559","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":"2026-05-18T00:13:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xhr+PMaZvpMPD6GIoS4yrjJylrkynX9LA+Hd9ObLPV7JfmHPyNrxjci8nFv5tOmgPd8JH62snUcf/cpwZ9BLBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T14:57:45.803825Z"},"content_sha256":"955b583f460f8f05cb0847a0366a2c799dc79103d0aa2dd14d0d4ffc735a30d6","schema_version":"1.0","event_id":"sha256:955b583f460f8f05cb0847a0366a2c799dc79103d0aa2dd14d0d4ffc735a30d6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5SKNTGLAAFPG7V3TF33DF2HSWA/bundle.json","state_url":"https://pith.science/pith/5SKNTGLAAFPG7V3TF33DF2HSWA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5SKNTGLAAFPG7V3TF33DF2HSWA/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":"2026-05-25T14:57:45Z","links":{"resolver":"https://pith.science/pith/5SKNTGLAAFPG7V3TF33DF2HSWA","bundle":"https://pith.science/pith/5SKNTGLAAFPG7V3TF33DF2HSWA/bundle.json","state":"https://pith.science/pith/5SKNTGLAAFPG7V3TF33DF2HSWA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5SKNTGLAAFPG7V3TF33DF2HSWA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:5SKNTGLAAFPG7V3TF33DF2HSWA","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":"138352b1eda421432d5481548296f5542c8a8fc12f12932df74da3b1ae55ac74","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-18T18:10:39Z","title_canon_sha256":"a30c6b5036366e79f924ca2915ea174e45ab2b11ad959743316f8e9354ab9a0d"},"schema_version":"1.0","source":{"id":"1712.06559","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.06559","created_at":"2026-05-18T00:13:10Z"},{"alias_kind":"arxiv_version","alias_value":"1712.06559v3","created_at":"2026-05-18T00:13:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.06559","created_at":"2026-05-18T00:13:10Z"},{"alias_kind":"pith_short_12","alias_value":"5SKNTGLAAFPG","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"5SKNTGLAAFPG7V3T","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"5SKNTGLA","created_at":"2026-05-18T12:31:00Z"}],"graph_snapshots":[{"event_id":"sha256:955b583f460f8f05cb0847a0366a2c799dc79103d0aa2dd14d0d4ffc735a30d6","target":"graph","created_at":"2026-05-18T00:13:10Z","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 aim to formally explain the phenomenon of fast convergence of SGD observed in modern machine learning. The key observation is that most modern learning architectures are over-parametrized and are trained to interpolate the data by driving the empirical loss (classification and regression) close to zero. While it is still unclear why these interpolated solutions perform well on test data, we show that these regimes allow for fast convergence of SGD, comparable in number of iterations to full gradient descent.\n  For convex loss functions we obtain an exponential convergence boun","authors_text":"Mikhail Belkin, Raef Bassily, Siyuan Ma","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-18T18:10:39Z","title":"The Power of Interpolation: Understanding the Effectiveness of SGD in Modern Over-parametrized Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.06559","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":"sha256:0d2f51fd61e68245f448df08f8964bd702373fb50ab83da708bc519a8f9262bc","target":"record","created_at":"2026-05-18T00:13:10Z","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":"138352b1eda421432d5481548296f5542c8a8fc12f12932df74da3b1ae55ac74","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-18T18:10:39Z","title_canon_sha256":"a30c6b5036366e79f924ca2915ea174e45ab2b11ad959743316f8e9354ab9a0d"},"schema_version":"1.0","source":{"id":"1712.06559","kind":"arxiv","version":3}},"canonical_sha256":"ec94d99960015e6fd7732ef632e8f2b0376ad761a794790a82e120201dcdea4c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ec94d99960015e6fd7732ef632e8f2b0376ad761a794790a82e120201dcdea4c","first_computed_at":"2026-05-18T00:13:10.647994Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:13:10.647994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"M6uuEe5og+pq3d9fmdLffQktD8l486lx1Gdu5xuSkGzdhMPwSMxPlMF+ntiqBIRXlKZ31KDJ2O5fq0+sID8KDw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:13:10.648646Z","signed_message":"canonical_sha256_bytes"},"source_id":"1712.06559","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0d2f51fd61e68245f448df08f8964bd702373fb50ab83da708bc519a8f9262bc","sha256:955b583f460f8f05cb0847a0366a2c799dc79103d0aa2dd14d0d4ffc735a30d6"],"state_sha256":"7f0a825b998ff2b875371f3f843a6402fd584311d7656488a60f01886232bfb0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CQnf1c0Npd9IHmBEuPe/rQma1zYOX5kqbevw69RHOdGGSAeSvhWIYYNTPmSBZt/PJz56+DG28Jlr8+YhHSZ5CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T14:57:45.807645Z","bundle_sha256":"c48290fc3158514ca96861d1eb799967568d5a30691c590905aa1e320d71bb66"}}