{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:BUJQOZ7TGG4QJEFHL3HO5OB36X","short_pith_number":"pith:BUJQOZ7T","canonical_record":{"source":{"id":"1402.7001","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-02-27T18:31:33Z","cross_cats_sorted":[],"title_canon_sha256":"f8c6b328a7a281eb3c8a7c298760999433a9c132970b8e62d2311f00d8469ca6","abstract_canon_sha256":"085a261634f0277bc9908a012296176cced5b56de7b1ba664003f6cab8ffb2fc"},"schema_version":"1.0"},"canonical_sha256":"0d130767f331b90490a75eceeeb83bf5e56e2e100d53efd0ba700aece639288b","source":{"kind":"arxiv","id":"1402.7001","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1402.7001","created_at":"2026-05-18T02:57:36Z"},{"alias_kind":"arxiv_version","alias_value":"1402.7001v1","created_at":"2026-05-18T02:57:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1402.7001","created_at":"2026-05-18T02:57:36Z"},{"alias_kind":"pith_short_12","alias_value":"BUJQOZ7TGG4Q","created_at":"2026-05-18T12:28:22Z"},{"alias_kind":"pith_short_16","alias_value":"BUJQOZ7TGG4QJEFH","created_at":"2026-05-18T12:28:22Z"},{"alias_kind":"pith_short_8","alias_value":"BUJQOZ7T","created_at":"2026-05-18T12:28:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:BUJQOZ7TGG4QJEFHL3HO5OB36X","target":"record","payload":{"canonical_record":{"source":{"id":"1402.7001","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-02-27T18:31:33Z","cross_cats_sorted":[],"title_canon_sha256":"f8c6b328a7a281eb3c8a7c298760999433a9c132970b8e62d2311f00d8469ca6","abstract_canon_sha256":"085a261634f0277bc9908a012296176cced5b56de7b1ba664003f6cab8ffb2fc"},"schema_version":"1.0"},"canonical_sha256":"0d130767f331b90490a75eceeeb83bf5e56e2e100d53efd0ba700aece639288b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:57:36.449564Z","signature_b64":"+61sqSn/72OZOTSyHTznX6qy3MHiJsOf0/xQdQZn6q5CVO94poX82YN0Y13cmIawGvrLHqFz/RQuE4vTxHSwBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d130767f331b90490a75eceeeb83bf5e56e2e100d53efd0ba700aece639288b","last_reissued_at":"2026-05-18T02:57:36.448971Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:57:36.448971Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1402.7001","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":"2026-05-18T02:57:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bPTvkG5YsLIYD9icJgmnVQri2hkrrRWpvG6x3LfzuJlihTrtzSoJiK/B+o1nhJJmMXHkUcQGHt75sQMcQiZPAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T16:12:15.786712Z"},"content_sha256":"a7934d99394b2d4365d9a105e1409dfc4c87d08ce94fc03a3f180a97a461c411","schema_version":"1.0","event_id":"sha256:a7934d99394b2d4365d9a105e1409dfc4c87d08ce94fc03a3f180a97a461c411"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:BUJQOZ7TGG4QJEFHL3HO5OB36X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Marginalizing Corrupted Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Kilian Weinberger, Laurens van der Maaten, Minmin Chen, Stephen Tyree","submitted_at":"2014-02-27T18:31:33Z","abstract_excerpt":"The goal of machine learning is to develop predictors that generalize well to test data. Ideally, this is achieved by training on an almost infinitely large training data set that captures all variations in the data distribution. In practical learning settings, however, we do not have infinite data and our predictors may overfit. Overfitting may be combatted, for example, by adding a regularizer to the training objective or by defining a prior over the model parameters and performing Bayesian inference. In this paper, we propose a third, alternative approach to combat overfitting: we extend th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1402.7001","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":"2026-05-18T02:57:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kWIlPvOse7jO4OctwT4Q5bkwJryNETnvDpfcBFmullvQo9T78lYLEkfveS3BEGrRGwMsLKKLnN7eAtQ04f2MDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T16:12:15.787421Z"},"content_sha256":"8d5e0b71545ec593de83f104ade94ceef54a1b13566c748e9ceeaf37848efff8","schema_version":"1.0","event_id":"sha256:8d5e0b71545ec593de83f104ade94ceef54a1b13566c748e9ceeaf37848efff8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BUJQOZ7TGG4QJEFHL3HO5OB36X/bundle.json","state_url":"https://pith.science/pith/BUJQOZ7TGG4QJEFHL3HO5OB36X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BUJQOZ7TGG4QJEFHL3HO5OB36X/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":"2026-05-25T16:12:15Z","links":{"resolver":"https://pith.science/pith/BUJQOZ7TGG4QJEFHL3HO5OB36X","bundle":"https://pith.science/pith/BUJQOZ7TGG4QJEFHL3HO5OB36X/bundle.json","state":"https://pith.science/pith/BUJQOZ7TGG4QJEFHL3HO5OB36X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BUJQOZ7TGG4QJEFHL3HO5OB36X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:BUJQOZ7TGG4QJEFHL3HO5OB36X","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":"085a261634f0277bc9908a012296176cced5b56de7b1ba664003f6cab8ffb2fc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-02-27T18:31:33Z","title_canon_sha256":"f8c6b328a7a281eb3c8a7c298760999433a9c132970b8e62d2311f00d8469ca6"},"schema_version":"1.0","source":{"id":"1402.7001","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1402.7001","created_at":"2026-05-18T02:57:36Z"},{"alias_kind":"arxiv_version","alias_value":"1402.7001v1","created_at":"2026-05-18T02:57:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1402.7001","created_at":"2026-05-18T02:57:36Z"},{"alias_kind":"pith_short_12","alias_value":"BUJQOZ7TGG4Q","created_at":"2026-05-18T12:28:22Z"},{"alias_kind":"pith_short_16","alias_value":"BUJQOZ7TGG4QJEFH","created_at":"2026-05-18T12:28:22Z"},{"alias_kind":"pith_short_8","alias_value":"BUJQOZ7T","created_at":"2026-05-18T12:28:22Z"}],"graph_snapshots":[{"event_id":"sha256:8d5e0b71545ec593de83f104ade94ceef54a1b13566c748e9ceeaf37848efff8","target":"graph","created_at":"2026-05-18T02:57:36Z","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":"The goal of machine learning is to develop predictors that generalize well to test data. Ideally, this is achieved by training on an almost infinitely large training data set that captures all variations in the data distribution. In practical learning settings, however, we do not have infinite data and our predictors may overfit. Overfitting may be combatted, for example, by adding a regularizer to the training objective or by defining a prior over the model parameters and performing Bayesian inference. In this paper, we propose a third, alternative approach to combat overfitting: we extend th","authors_text":"Kilian Weinberger, Laurens van der Maaten, Minmin Chen, Stephen Tyree","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-02-27T18:31:33Z","title":"Marginalizing Corrupted Features"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1402.7001","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:a7934d99394b2d4365d9a105e1409dfc4c87d08ce94fc03a3f180a97a461c411","target":"record","created_at":"2026-05-18T02:57:36Z","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":"085a261634f0277bc9908a012296176cced5b56de7b1ba664003f6cab8ffb2fc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-02-27T18:31:33Z","title_canon_sha256":"f8c6b328a7a281eb3c8a7c298760999433a9c132970b8e62d2311f00d8469ca6"},"schema_version":"1.0","source":{"id":"1402.7001","kind":"arxiv","version":1}},"canonical_sha256":"0d130767f331b90490a75eceeeb83bf5e56e2e100d53efd0ba700aece639288b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0d130767f331b90490a75eceeeb83bf5e56e2e100d53efd0ba700aece639288b","first_computed_at":"2026-05-18T02:57:36.448971Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:57:36.448971Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+61sqSn/72OZOTSyHTznX6qy3MHiJsOf0/xQdQZn6q5CVO94poX82YN0Y13cmIawGvrLHqFz/RQuE4vTxHSwBg==","signature_status":"signed_v1","signed_at":"2026-05-18T02:57:36.449564Z","signed_message":"canonical_sha256_bytes"},"source_id":"1402.7001","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a7934d99394b2d4365d9a105e1409dfc4c87d08ce94fc03a3f180a97a461c411","sha256:8d5e0b71545ec593de83f104ade94ceef54a1b13566c748e9ceeaf37848efff8"],"state_sha256":"ceb9af245f59c96f38ee44033b643031130fd7913024486796f210248c50ba64"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F4RSA+Pl8/p/HNp4icKS3Cj2iiHmI0r6psJAPK81kDiNoHnQDAPcYgjgjep2NisOlZycQqCeWJTw439kEuH8Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T16:12:15.791214Z","bundle_sha256":"fdab8b521fa41d4a7f608bebbe77ca1aaf51126726500a6bd8c1ba0cbd829c02"}}