{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:DTSO2RGDOXECDOMXZ75F5ZCQ6R","short_pith_number":"pith:DTSO2RGD","canonical_record":{"source":{"id":"1412.4736","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-12-15T19:40:46Z","cross_cats_sorted":["cs.AI","cs.NE","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"e0c1834ecdade3c30fe199027689702dc55d544ef7552665578af601e5aec264","abstract_canon_sha256":"f201a55b0aff96892ee52202bfb80272c696e9e3a3c24b9aaf3b53c1604b5098"},"schema_version":"1.0"},"canonical_sha256":"1ce4ed44c375c821b997cffa5ee450f45613d6341393ae10ff1d695a0b854895","source":{"kind":"arxiv","id":"1412.4736","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1412.4736","created_at":"2026-05-18T00:50:31Z"},{"alias_kind":"arxiv_version","alias_value":"1412.4736v4","created_at":"2026-05-18T00:50:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1412.4736","created_at":"2026-05-18T00:50:31Z"},{"alias_kind":"pith_short_12","alias_value":"DTSO2RGDOXEC","created_at":"2026-05-18T12:28:25Z"},{"alias_kind":"pith_short_16","alias_value":"DTSO2RGDOXECDOMX","created_at":"2026-05-18T12:28:25Z"},{"alias_kind":"pith_short_8","alias_value":"DTSO2RGD","created_at":"2026-05-18T12:28:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:DTSO2RGDOXECDOMXZ75F5ZCQ6R","target":"record","payload":{"canonical_record":{"source":{"id":"1412.4736","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-12-15T19:40:46Z","cross_cats_sorted":["cs.AI","cs.NE","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"e0c1834ecdade3c30fe199027689702dc55d544ef7552665578af601e5aec264","abstract_canon_sha256":"f201a55b0aff96892ee52202bfb80272c696e9e3a3c24b9aaf3b53c1604b5098"},"schema_version":"1.0"},"canonical_sha256":"1ce4ed44c375c821b997cffa5ee450f45613d6341393ae10ff1d695a0b854895","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:50:31.337477Z","signature_b64":"sA6qxgwMuDlnY7p8XICv3EhehGw8OobhT51DCRpyW/j9E1F3D9FEph0vnsjy9Fd6jAk5yWhtzOCepaOtUaAhBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ce4ed44c375c821b997cffa5ee450f45613d6341393ae10ff1d695a0b854895","last_reissued_at":"2026-05-18T00:50:31.336835Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:50:31.336835Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1412.4736","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:50:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CtfL5Gl0snxUPOSTOsWsjOQJPz4ywPG9DhGN9QLd9mbiA4JVg4Kf8Sr2tSGWDfwbyi6cGcwF9M8YNmV5PCKRBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T02:38:20.892933Z"},"content_sha256":"b596de993a1f7f66d76b73495febd4560459df3eb095081f5a43d39c8d5abb13","schema_version":"1.0","event_id":"sha256:b596de993a1f7f66d76b73495febd4560459df3eb095081f5a43d39c8d5abb13"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:DTSO2RGDOXECDOMXZ75F5ZCQ6R","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the Inductive Bias of Dropout","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"David P. Helmbold, Philip M. Long","submitted_at":"2014-12-15T19:40:46Z","abstract_excerpt":"Dropout is a simple but effective technique for learning in neural networks and other settings. A sound theoretical understanding of dropout is needed to determine when dropout should be applied and how to use it most effectively. In this paper we continue the exploration of dropout as a regularizer pioneered by Wager, et.al. We focus on linear classification where a convex proxy to the misclassification loss (i.e. the logistic loss used in logistic regression) is minimized. We show: (a) when the dropout-regularized criterion has a unique minimizer, (b) when the dropout-regularization penalty "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1412.4736","kind":"arxiv","version":4},"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":"2026-05-18T00:50:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pNBcZC8vKwWGaSKP+ghOI7TWLIRBbG2DmoaG1M4Oiq2jMOJ9NBTr5d3Hf7HjCbhDdL9szlvnKcyO3VCA3HwVBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T02:38:20.893288Z"},"content_sha256":"07d77daa032b8092d97c77b08acbd77f40d5ed165740a90669a37775cb312a76","schema_version":"1.0","event_id":"sha256:07d77daa032b8092d97c77b08acbd77f40d5ed165740a90669a37775cb312a76"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DTSO2RGDOXECDOMXZ75F5ZCQ6R/bundle.json","state_url":"https://pith.science/pith/DTSO2RGDOXECDOMXZ75F5ZCQ6R/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DTSO2RGDOXECDOMXZ75F5ZCQ6R/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":"2026-06-03T02:38:20Z","links":{"resolver":"https://pith.science/pith/DTSO2RGDOXECDOMXZ75F5ZCQ6R","bundle":"https://pith.science/pith/DTSO2RGDOXECDOMXZ75F5ZCQ6R/bundle.json","state":"https://pith.science/pith/DTSO2RGDOXECDOMXZ75F5ZCQ6R/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DTSO2RGDOXECDOMXZ75F5ZCQ6R/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:DTSO2RGDOXECDOMXZ75F5ZCQ6R","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":"f201a55b0aff96892ee52202bfb80272c696e9e3a3c24b9aaf3b53c1604b5098","cross_cats_sorted":["cs.AI","cs.NE","math.ST","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-12-15T19:40:46Z","title_canon_sha256":"e0c1834ecdade3c30fe199027689702dc55d544ef7552665578af601e5aec264"},"schema_version":"1.0","source":{"id":"1412.4736","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1412.4736","created_at":"2026-05-18T00:50:31Z"},{"alias_kind":"arxiv_version","alias_value":"1412.4736v4","created_at":"2026-05-18T00:50:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1412.4736","created_at":"2026-05-18T00:50:31Z"},{"alias_kind":"pith_short_12","alias_value":"DTSO2RGDOXEC","created_at":"2026-05-18T12:28:25Z"},{"alias_kind":"pith_short_16","alias_value":"DTSO2RGDOXECDOMX","created_at":"2026-05-18T12:28:25Z"},{"alias_kind":"pith_short_8","alias_value":"DTSO2RGD","created_at":"2026-05-18T12:28:25Z"}],"graph_snapshots":[{"event_id":"sha256:07d77daa032b8092d97c77b08acbd77f40d5ed165740a90669a37775cb312a76","target":"graph","created_at":"2026-05-18T00:50:31Z","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":"Dropout is a simple but effective technique for learning in neural networks and other settings. A sound theoretical understanding of dropout is needed to determine when dropout should be applied and how to use it most effectively. In this paper we continue the exploration of dropout as a regularizer pioneered by Wager, et.al. We focus on linear classification where a convex proxy to the misclassification loss (i.e. the logistic loss used in logistic regression) is minimized. We show: (a) when the dropout-regularized criterion has a unique minimizer, (b) when the dropout-regularization penalty ","authors_text":"David P. Helmbold, Philip M. Long","cross_cats":["cs.AI","cs.NE","math.ST","stat.ML","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-12-15T19:40:46Z","title":"On the Inductive Bias of Dropout"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1412.4736","kind":"arxiv","version":4},"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:b596de993a1f7f66d76b73495febd4560459df3eb095081f5a43d39c8d5abb13","target":"record","created_at":"2026-05-18T00:50:31Z","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":"f201a55b0aff96892ee52202bfb80272c696e9e3a3c24b9aaf3b53c1604b5098","cross_cats_sorted":["cs.AI","cs.NE","math.ST","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-12-15T19:40:46Z","title_canon_sha256":"e0c1834ecdade3c30fe199027689702dc55d544ef7552665578af601e5aec264"},"schema_version":"1.0","source":{"id":"1412.4736","kind":"arxiv","version":4}},"canonical_sha256":"1ce4ed44c375c821b997cffa5ee450f45613d6341393ae10ff1d695a0b854895","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1ce4ed44c375c821b997cffa5ee450f45613d6341393ae10ff1d695a0b854895","first_computed_at":"2026-05-18T00:50:31.336835Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:50:31.336835Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sA6qxgwMuDlnY7p8XICv3EhehGw8OobhT51DCRpyW/j9E1F3D9FEph0vnsjy9Fd6jAk5yWhtzOCepaOtUaAhBw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:50:31.337477Z","signed_message":"canonical_sha256_bytes"},"source_id":"1412.4736","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b596de993a1f7f66d76b73495febd4560459df3eb095081f5a43d39c8d5abb13","sha256:07d77daa032b8092d97c77b08acbd77f40d5ed165740a90669a37775cb312a76"],"state_sha256":"5594ce389ce5ac85492d5b559fdb80058695fe82248de1a1239b0c84db502837"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oPjKpxCOuI75APMg31KZbfEvDEvOx7BxyojBOFnpDwK1BXEvT/y+j2MfoU2WVuBFn6fVzxfvwLOXVAj+Hp9oAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T02:38:20.895244Z","bundle_sha256":"ac27a638732698483fd9c0e5a8b5c4df99e29eb6f2c139b3920d776ebd6a4206"}}