{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:YYMCQBW5OCYZCOS66NZSHDIX4C","short_pith_number":"pith:YYMCQBW5","canonical_record":{"source":{"id":"1705.03071","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-08T20:12:08Z","cross_cats_sorted":[],"title_canon_sha256":"5580f022590d5b8965945d053f7bb68d5bb55d8f187789e6a9d667eb004d7e5d","abstract_canon_sha256":"d9cafd6e17d4600fedc4edcb627e12c4bf1caeb122f81971bdf21b3dd7d87212"},"schema_version":"1.0"},"canonical_sha256":"c6182806dd70b1913a5ef373238d17e0a9f9bfb3e788270414136fd25bbe4039","source":{"kind":"arxiv","id":"1705.03071","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.03071","created_at":"2026-05-18T00:44:50Z"},{"alias_kind":"arxiv_version","alias_value":"1705.03071v1","created_at":"2026-05-18T00:44:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.03071","created_at":"2026-05-18T00:44:50Z"},{"alias_kind":"pith_short_12","alias_value":"YYMCQBW5OCYZ","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_16","alias_value":"YYMCQBW5OCYZCOS6","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_8","alias_value":"YYMCQBW5","created_at":"2026-05-18T12:31:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:YYMCQBW5OCYZCOS66NZSHDIX4C","target":"record","payload":{"canonical_record":{"source":{"id":"1705.03071","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-08T20:12:08Z","cross_cats_sorted":[],"title_canon_sha256":"5580f022590d5b8965945d053f7bb68d5bb55d8f187789e6a9d667eb004d7e5d","abstract_canon_sha256":"d9cafd6e17d4600fedc4edcb627e12c4bf1caeb122f81971bdf21b3dd7d87212"},"schema_version":"1.0"},"canonical_sha256":"c6182806dd70b1913a5ef373238d17e0a9f9bfb3e788270414136fd25bbe4039","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:44:50.782336Z","signature_b64":"6vrDuGhuhPZhuBLQc2kBtKytot9qiP3kEuk8x3nEMOkRGEk6QNDFJGMeffGxHSWbyVckQwMqJ3OkGeTiDP1mDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6182806dd70b1913a5ef373238d17e0a9f9bfb3e788270414136fd25bbe4039","last_reissued_at":"2026-05-18T00:44:50.781644Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:44:50.781644Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1705.03071","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":"2026-05-18T00:44:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fZoOErM9bL+JJZOXirKcx7EDUnBPeJLnh3n+PcEnQxK6PyARk2VEAezsC3ztriKmU6s2ikj9MR5zUysCEQxwBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T06:44:50.738002Z"},"content_sha256":"39aea1197887c55e5a3843d1a64137b4ebc474b5a46dbf8f853d6714392af9ca","schema_version":"1.0","event_id":"sha256:39aea1197887c55e5a3843d1a64137b4ebc474b5a46dbf8f853d6714392af9ca"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:YYMCQBW5OCYZCOS66NZSHDIX4C","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Geometry of Optimization and Implicit Regularization in Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Behnam Neyshabur, Nathan Srebro, Ruslan Salakhutdinov, Ryota Tomioka","submitted_at":"2017-05-08T20:12:08Z","abstract_excerpt":"We argue that the optimization plays a crucial role in generalization of deep learning models through implicit regularization. We do this by demonstrating that generalization ability is not controlled by network size but rather by some other implicit control. We then demonstrate how changing the empirical optimization procedure can improve generalization, even if actual optimization quality is not affected. We do so by studying the geometry of the parameter space of deep networks, and devising an optimization algorithm attuned to this geometry."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.03071","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":"2026-05-18T00:44:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lXRwUM7IsNlbr5yWfpVTNU5V+5YcBWRoA+UaKOLCCTefb/aHLb3J3wne0RZ94jKakQuh9hYJ4PNB1oBXQqHUDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T06:44:50.738730Z"},"content_sha256":"d6e1bbdfda709dd2c58f08715167f74f7a605e65d65ea62e5923cb6e4d6db954","schema_version":"1.0","event_id":"sha256:d6e1bbdfda709dd2c58f08715167f74f7a605e65d65ea62e5923cb6e4d6db954"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YYMCQBW5OCYZCOS66NZSHDIX4C/bundle.json","state_url":"https://pith.science/pith/YYMCQBW5OCYZCOS66NZSHDIX4C/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YYMCQBW5OCYZCOS66NZSHDIX4C/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":"2026-05-27T06:44:50Z","links":{"resolver":"https://pith.science/pith/YYMCQBW5OCYZCOS66NZSHDIX4C","bundle":"https://pith.science/pith/YYMCQBW5OCYZCOS66NZSHDIX4C/bundle.json","state":"https://pith.science/pith/YYMCQBW5OCYZCOS66NZSHDIX4C/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YYMCQBW5OCYZCOS66NZSHDIX4C/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:YYMCQBW5OCYZCOS66NZSHDIX4C","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":"d9cafd6e17d4600fedc4edcb627e12c4bf1caeb122f81971bdf21b3dd7d87212","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-08T20:12:08Z","title_canon_sha256":"5580f022590d5b8965945d053f7bb68d5bb55d8f187789e6a9d667eb004d7e5d"},"schema_version":"1.0","source":{"id":"1705.03071","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.03071","created_at":"2026-05-18T00:44:50Z"},{"alias_kind":"arxiv_version","alias_value":"1705.03071v1","created_at":"2026-05-18T00:44:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.03071","created_at":"2026-05-18T00:44:50Z"},{"alias_kind":"pith_short_12","alias_value":"YYMCQBW5OCYZ","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_16","alias_value":"YYMCQBW5OCYZCOS6","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_8","alias_value":"YYMCQBW5","created_at":"2026-05-18T12:31:59Z"}],"graph_snapshots":[{"event_id":"sha256:d6e1bbdfda709dd2c58f08715167f74f7a605e65d65ea62e5923cb6e4d6db954","target":"graph","created_at":"2026-05-18T00:44:50Z","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":"We argue that the optimization plays a crucial role in generalization of deep learning models through implicit regularization. We do this by demonstrating that generalization ability is not controlled by network size but rather by some other implicit control. We then demonstrate how changing the empirical optimization procedure can improve generalization, even if actual optimization quality is not affected. We do so by studying the geometry of the parameter space of deep networks, and devising an optimization algorithm attuned to this geometry.","authors_text":"Behnam Neyshabur, Nathan Srebro, Ruslan Salakhutdinov, Ryota Tomioka","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-08T20:12:08Z","title":"Geometry of Optimization and Implicit Regularization in Deep Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.03071","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":"sha256:39aea1197887c55e5a3843d1a64137b4ebc474b5a46dbf8f853d6714392af9ca","target":"record","created_at":"2026-05-18T00:44:50Z","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":"d9cafd6e17d4600fedc4edcb627e12c4bf1caeb122f81971bdf21b3dd7d87212","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-08T20:12:08Z","title_canon_sha256":"5580f022590d5b8965945d053f7bb68d5bb55d8f187789e6a9d667eb004d7e5d"},"schema_version":"1.0","source":{"id":"1705.03071","kind":"arxiv","version":1}},"canonical_sha256":"c6182806dd70b1913a5ef373238d17e0a9f9bfb3e788270414136fd25bbe4039","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c6182806dd70b1913a5ef373238d17e0a9f9bfb3e788270414136fd25bbe4039","first_computed_at":"2026-05-18T00:44:50.781644Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:44:50.781644Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6vrDuGhuhPZhuBLQc2kBtKytot9qiP3kEuk8x3nEMOkRGEk6QNDFJGMeffGxHSWbyVckQwMqJ3OkGeTiDP1mDw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:44:50.782336Z","signed_message":"canonical_sha256_bytes"},"source_id":"1705.03071","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:39aea1197887c55e5a3843d1a64137b4ebc474b5a46dbf8f853d6714392af9ca","sha256:d6e1bbdfda709dd2c58f08715167f74f7a605e65d65ea62e5923cb6e4d6db954"],"state_sha256":"6a8850e8ef269664c37cf510e4d9b0059c5bb3bbafe6ff4ab4ac15d5de9e1d1b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"56ku8akYZ9W7oc4m5J2YYgb4vk17ZqqHrXgedcVt+zd9oMFmGm2iCbMS9tFNDI30ys6+uI9/2+GwtY9fiEdVBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T06:44:50.742716Z","bundle_sha256":"2a3be4b4f8e4186a1da177de9214929c3f27e44154b188e6493ddebf50fbc48f"}}