{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:UM3M4CWZSC4YCJNRMMJTKIM2YK","short_pith_number":"pith:UM3M4CWZ","canonical_record":{"source":{"id":"1508.02790","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2015-08-12T01:11:47Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0c1ef051f95db30abae2fd65240bc6036d041dedccee272d86eaffc4ff69ff35","abstract_canon_sha256":"facb2a90921c0b4eef4a780351c35699b02b781b48eeb550311cb8b3a130a5cd"},"schema_version":"1.0"},"canonical_sha256":"a336ce0ad990b98125b1631335219ac2ada632a4590415d7ed9da3d66369fa5a","source":{"kind":"arxiv","id":"1508.02790","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1508.02790","created_at":"2026-05-18T01:35:26Z"},{"alias_kind":"arxiv_version","alias_value":"1508.02790v1","created_at":"2026-05-18T01:35:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1508.02790","created_at":"2026-05-18T01:35:26Z"},{"alias_kind":"pith_short_12","alias_value":"UM3M4CWZSC4Y","created_at":"2026-05-18T12:29:44Z"},{"alias_kind":"pith_short_16","alias_value":"UM3M4CWZSC4YCJNR","created_at":"2026-05-18T12:29:44Z"},{"alias_kind":"pith_short_8","alias_value":"UM3M4CWZ","created_at":"2026-05-18T12:29:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:UM3M4CWZSC4YCJNRMMJTKIM2YK","target":"record","payload":{"canonical_record":{"source":{"id":"1508.02790","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2015-08-12T01:11:47Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0c1ef051f95db30abae2fd65240bc6036d041dedccee272d86eaffc4ff69ff35","abstract_canon_sha256":"facb2a90921c0b4eef4a780351c35699b02b781b48eeb550311cb8b3a130a5cd"},"schema_version":"1.0"},"canonical_sha256":"a336ce0ad990b98125b1631335219ac2ada632a4590415d7ed9da3d66369fa5a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:35:26.189202Z","signature_b64":"3Q4OvV7/1HGC+1Dc17G/5PMJbaDzjWfCRenmB1PgfQpDM+XCzYGKNAD0yIqdLuMxqF5wQsD9k59WWmGQ5kPlDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a336ce0ad990b98125b1631335219ac2ada632a4590415d7ed9da3d66369fa5a","last_reissued_at":"2026-05-18T01:35:26.188556Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:35:26.188556Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1508.02790","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":"2026-05-18T01:35:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ISCpZhOyplmoKjbujED9+FgcgATTKgv6ylpjIPsQI2GHUdWZqoWDdqCivRfPmlXGw1YB7bfEwZuT9piM1nH9Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T21:13:55.968498Z"},"content_sha256":"8fc1ff646c116dffa8097e6586dce3ca37b4894dade2ebb640dd29f388104f59","schema_version":"1.0","event_id":"sha256:8fc1ff646c116dffa8097e6586dce3ca37b4894dade2ebb640dd29f388104f59"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:UM3M4CWZSC4YCJNRMMJTKIM2YK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the Convergence of SGD Training of Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.NE","authors_text":"Thomas M. Breuel","submitted_at":"2015-08-12T01:11:47Z","abstract_excerpt":"Neural networks are usually trained by some form of stochastic gradient descent (SGD)). A number of strategies are in common use intended to improve SGD optimization, such as learning rate schedules, momentum, and batching. These are motivated by ideas about the occurrence of local minima at different scales, valleys, and other phenomena in the objective function. Empirical results presented here suggest that these phenomena are not significant factors in SGD optimization of MLP-related objective functions, and that the behavior of stochastic gradient descent in these problems is better descri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1508.02790","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":"2026-05-18T01:35:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3HsEoRUNQfX0CTruuAB4njdS1lzbz5PSLJgjO3keBz3LS4LMcSfDTu5jsnyMFMdWvK1Iak++dssuZKADzUVGBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T21:13:55.968859Z"},"content_sha256":"a344fa760cd78a171f980a7c4fc8adadcfa8529433e92b1ada4c626f009ae9fb","schema_version":"1.0","event_id":"sha256:a344fa760cd78a171f980a7c4fc8adadcfa8529433e92b1ada4c626f009ae9fb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UM3M4CWZSC4YCJNRMMJTKIM2YK/bundle.json","state_url":"https://pith.science/pith/UM3M4CWZSC4YCJNRMMJTKIM2YK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UM3M4CWZSC4YCJNRMMJTKIM2YK/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":"2026-06-10T21:13:55Z","links":{"resolver":"https://pith.science/pith/UM3M4CWZSC4YCJNRMMJTKIM2YK","bundle":"https://pith.science/pith/UM3M4CWZSC4YCJNRMMJTKIM2YK/bundle.json","state":"https://pith.science/pith/UM3M4CWZSC4YCJNRMMJTKIM2YK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UM3M4CWZSC4YCJNRMMJTKIM2YK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:UM3M4CWZSC4YCJNRMMJTKIM2YK","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":"facb2a90921c0b4eef4a780351c35699b02b781b48eeb550311cb8b3a130a5cd","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2015-08-12T01:11:47Z","title_canon_sha256":"0c1ef051f95db30abae2fd65240bc6036d041dedccee272d86eaffc4ff69ff35"},"schema_version":"1.0","source":{"id":"1508.02790","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1508.02790","created_at":"2026-05-18T01:35:26Z"},{"alias_kind":"arxiv_version","alias_value":"1508.02790v1","created_at":"2026-05-18T01:35:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1508.02790","created_at":"2026-05-18T01:35:26Z"},{"alias_kind":"pith_short_12","alias_value":"UM3M4CWZSC4Y","created_at":"2026-05-18T12:29:44Z"},{"alias_kind":"pith_short_16","alias_value":"UM3M4CWZSC4YCJNR","created_at":"2026-05-18T12:29:44Z"},{"alias_kind":"pith_short_8","alias_value":"UM3M4CWZ","created_at":"2026-05-18T12:29:44Z"}],"graph_snapshots":[{"event_id":"sha256:a344fa760cd78a171f980a7c4fc8adadcfa8529433e92b1ada4c626f009ae9fb","target":"graph","created_at":"2026-05-18T01:35:26Z","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 networks are usually trained by some form of stochastic gradient descent (SGD)). A number of strategies are in common use intended to improve SGD optimization, such as learning rate schedules, momentum, and batching. These are motivated by ideas about the occurrence of local minima at different scales, valleys, and other phenomena in the objective function. Empirical results presented here suggest that these phenomena are not significant factors in SGD optimization of MLP-related objective functions, and that the behavior of stochastic gradient descent in these problems is better descri","authors_text":"Thomas M. Breuel","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2015-08-12T01:11:47Z","title":"On the Convergence of SGD Training of Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1508.02790","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":"sha256:8fc1ff646c116dffa8097e6586dce3ca37b4894dade2ebb640dd29f388104f59","target":"record","created_at":"2026-05-18T01:35:26Z","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":"facb2a90921c0b4eef4a780351c35699b02b781b48eeb550311cb8b3a130a5cd","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2015-08-12T01:11:47Z","title_canon_sha256":"0c1ef051f95db30abae2fd65240bc6036d041dedccee272d86eaffc4ff69ff35"},"schema_version":"1.0","source":{"id":"1508.02790","kind":"arxiv","version":1}},"canonical_sha256":"a336ce0ad990b98125b1631335219ac2ada632a4590415d7ed9da3d66369fa5a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a336ce0ad990b98125b1631335219ac2ada632a4590415d7ed9da3d66369fa5a","first_computed_at":"2026-05-18T01:35:26.188556Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:35:26.188556Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3Q4OvV7/1HGC+1Dc17G/5PMJbaDzjWfCRenmB1PgfQpDM+XCzYGKNAD0yIqdLuMxqF5wQsD9k59WWmGQ5kPlDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:35:26.189202Z","signed_message":"canonical_sha256_bytes"},"source_id":"1508.02790","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8fc1ff646c116dffa8097e6586dce3ca37b4894dade2ebb640dd29f388104f59","sha256:a344fa760cd78a171f980a7c4fc8adadcfa8529433e92b1ada4c626f009ae9fb"],"state_sha256":"97d9f7b501868ba8ba5811b805c1214b47f20f3a86bb6db5e6e7a0aa1963f166"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w8smnf5U01XoYTeATY7b62+sUya0JYQc3v4iaBxbxxtGPEawccpYJmqVRBL4UjtxHbPjE5xvVbRTmUuKwocDCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T21:13:55.970805Z","bundle_sha256":"30beea84afbc7df440a943d14fc4234d0a5c19a842878aa205f92a22cb2826a9"}}