{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:ZBC4WVEIFJ2YB76OJH2B6G7ELY","short_pith_number":"pith:ZBC4WVEI","canonical_record":{"source":{"id":"1503.02031","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-03-06T18:39:53Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"b6167da9f674138272db8c66bbbfe16e84d5eaf280974759956e10c469a41ebf","abstract_canon_sha256":"0ce5730780aff7a39c714b1f8324b28fa120a9032c42d041e52a9dc66d7e8e55"},"schema_version":"1.0"},"canonical_sha256":"c845cb54882a7580ffce49f41f1be45e2807792e6aabbf7b30f6c288ba685355","source":{"kind":"arxiv","id":"1503.02031","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1503.02031","created_at":"2026-05-18T02:25:27Z"},{"alias_kind":"arxiv_version","alias_value":"1503.02031v1","created_at":"2026-05-18T02:25:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1503.02031","created_at":"2026-05-18T02:25:27Z"},{"alias_kind":"pith_short_12","alias_value":"ZBC4WVEIFJ2Y","created_at":"2026-05-18T12:29:52Z"},{"alias_kind":"pith_short_16","alias_value":"ZBC4WVEIFJ2YB76O","created_at":"2026-05-18T12:29:52Z"},{"alias_kind":"pith_short_8","alias_value":"ZBC4WVEI","created_at":"2026-05-18T12:29:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:ZBC4WVEIFJ2YB76OJH2B6G7ELY","target":"record","payload":{"canonical_record":{"source":{"id":"1503.02031","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-03-06T18:39:53Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"b6167da9f674138272db8c66bbbfe16e84d5eaf280974759956e10c469a41ebf","abstract_canon_sha256":"0ce5730780aff7a39c714b1f8324b28fa120a9032c42d041e52a9dc66d7e8e55"},"schema_version":"1.0"},"canonical_sha256":"c845cb54882a7580ffce49f41f1be45e2807792e6aabbf7b30f6c288ba685355","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:25:27.040575Z","signature_b64":"MwH/HGkagTHzozSObUT5RTX2il7x00hSUkOhH3NQY1X4X0qCLs3rZNT12Y/4YwpuwRWMgoXeWY714K4vkgh0AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c845cb54882a7580ffce49f41f1be45e2807792e6aabbf7b30f6c288ba685355","last_reissued_at":"2026-05-18T02:25:27.039953Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:25:27.039953Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1503.02031","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":"2026-05-18T02:25:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H+8W+PfYb9X7qTuqldG3CJqyopUTw6NQ+BnjuEpWL+5sDgecxm7oSuviEPZOiSozsteAo/G2ZdD1zaJRHq00DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T21:07:25.582621Z"},"content_sha256":"b44ff0b00c6385804bf1a8c3869ee6a28a7bcbe8173e2f253ebd27ebc773c0ae","schema_version":"1.0","event_id":"sha256:b44ff0b00c6385804bf1a8c3869ee6a28a7bcbe8173e2f253ebd27ebc773c0ae"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:ZBC4WVEIFJ2YB76OJH2B6G7ELY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"To Drop or Not to Drop: Robustness, Consistency and Differential Privacy Properties of Dropout","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abhradeep Thakurta, Oliver Williams, Prateek Jain, Vivek Kulkarni","submitted_at":"2015-03-06T18:39:53Z","abstract_excerpt":"Training deep belief networks (DBNs) requires optimizing a non-convex function with an extremely large number of parameters. Naturally, existing gradient descent (GD) based methods are prone to arbitrarily poor local minima. In this paper, we rigorously show that such local minima can be avoided (upto an approximation error) by using the dropout technique, a widely used heuristic in this domain. In particular, we show that by randomly dropping a few nodes of a one-hidden layer neural network, the training objective function, up to a certain approximation error, decreases by a multiplicative fa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1503.02031","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":"2026-05-18T02:25:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YoFxHNUDr5Y+OFlpApzotbyvoCHLeNyEDrW4cCmRA/NAcw/qfL0dVoNBgLc4RbA50iMZfvTw7oAxViCzQB8bCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T21:07:25.582970Z"},"content_sha256":"c017e65f698d7aac3ea693d7ac37aeeafb48fb864111260e755ff7f1420e1ed7","schema_version":"1.0","event_id":"sha256:c017e65f698d7aac3ea693d7ac37aeeafb48fb864111260e755ff7f1420e1ed7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZBC4WVEIFJ2YB76OJH2B6G7ELY/bundle.json","state_url":"https://pith.science/pith/ZBC4WVEIFJ2YB76OJH2B6G7ELY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZBC4WVEIFJ2YB76OJH2B6G7ELY/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":"2026-06-26T21:07:25Z","links":{"resolver":"https://pith.science/pith/ZBC4WVEIFJ2YB76OJH2B6G7ELY","bundle":"https://pith.science/pith/ZBC4WVEIFJ2YB76OJH2B6G7ELY/bundle.json","state":"https://pith.science/pith/ZBC4WVEIFJ2YB76OJH2B6G7ELY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZBC4WVEIFJ2YB76OJH2B6G7ELY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:ZBC4WVEIFJ2YB76OJH2B6G7ELY","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":"0ce5730780aff7a39c714b1f8324b28fa120a9032c42d041e52a9dc66d7e8e55","cross_cats_sorted":["cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-03-06T18:39:53Z","title_canon_sha256":"b6167da9f674138272db8c66bbbfe16e84d5eaf280974759956e10c469a41ebf"},"schema_version":"1.0","source":{"id":"1503.02031","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1503.02031","created_at":"2026-05-18T02:25:27Z"},{"alias_kind":"arxiv_version","alias_value":"1503.02031v1","created_at":"2026-05-18T02:25:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1503.02031","created_at":"2026-05-18T02:25:27Z"},{"alias_kind":"pith_short_12","alias_value":"ZBC4WVEIFJ2Y","created_at":"2026-05-18T12:29:52Z"},{"alias_kind":"pith_short_16","alias_value":"ZBC4WVEIFJ2YB76O","created_at":"2026-05-18T12:29:52Z"},{"alias_kind":"pith_short_8","alias_value":"ZBC4WVEI","created_at":"2026-05-18T12:29:52Z"}],"graph_snapshots":[{"event_id":"sha256:c017e65f698d7aac3ea693d7ac37aeeafb48fb864111260e755ff7f1420e1ed7","target":"graph","created_at":"2026-05-18T02:25:27Z","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":"Training deep belief networks (DBNs) requires optimizing a non-convex function with an extremely large number of parameters. Naturally, existing gradient descent (GD) based methods are prone to arbitrarily poor local minima. In this paper, we rigorously show that such local minima can be avoided (upto an approximation error) by using the dropout technique, a widely used heuristic in this domain. In particular, we show that by randomly dropping a few nodes of a one-hidden layer neural network, the training objective function, up to a certain approximation error, decreases by a multiplicative fa","authors_text":"Abhradeep Thakurta, Oliver Williams, Prateek Jain, Vivek Kulkarni","cross_cats":["cs.NE","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-03-06T18:39:53Z","title":"To Drop or Not to Drop: Robustness, Consistency and Differential Privacy Properties of Dropout"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1503.02031","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:b44ff0b00c6385804bf1a8c3869ee6a28a7bcbe8173e2f253ebd27ebc773c0ae","target":"record","created_at":"2026-05-18T02:25:27Z","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":"0ce5730780aff7a39c714b1f8324b28fa120a9032c42d041e52a9dc66d7e8e55","cross_cats_sorted":["cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-03-06T18:39:53Z","title_canon_sha256":"b6167da9f674138272db8c66bbbfe16e84d5eaf280974759956e10c469a41ebf"},"schema_version":"1.0","source":{"id":"1503.02031","kind":"arxiv","version":1}},"canonical_sha256":"c845cb54882a7580ffce49f41f1be45e2807792e6aabbf7b30f6c288ba685355","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c845cb54882a7580ffce49f41f1be45e2807792e6aabbf7b30f6c288ba685355","first_computed_at":"2026-05-18T02:25:27.039953Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:25:27.039953Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MwH/HGkagTHzozSObUT5RTX2il7x00hSUkOhH3NQY1X4X0qCLs3rZNT12Y/4YwpuwRWMgoXeWY714K4vkgh0AQ==","signature_status":"signed_v1","signed_at":"2026-05-18T02:25:27.040575Z","signed_message":"canonical_sha256_bytes"},"source_id":"1503.02031","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b44ff0b00c6385804bf1a8c3869ee6a28a7bcbe8173e2f253ebd27ebc773c0ae","sha256:c017e65f698d7aac3ea693d7ac37aeeafb48fb864111260e755ff7f1420e1ed7"],"state_sha256":"297aa5afe58e354e14d76869c653f02ec84f22b551fece8b4c184ffbe3d39fd2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wOwGobbNvTCVTn1GVTHDfGWkroHKScxZGVwE6gYRFCdt53DnFiP2cM3nWzFfLm30QygWRe20BPmvdjypqoZtBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-26T21:07:25.584920Z","bundle_sha256":"003391f0b47577c081512d67927f3043f83f1c33f9e77d3f461a6b704c02649b"}}