{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2013:XGQIOVNYKUVXSF77B3UGAEB7R3","short_pith_number":"pith:XGQIOVNY","canonical_record":{"source":{"id":"1311.0701","kind":"arxiv","version":7},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2013-11-04T13:56:23Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"8cea681f21554e1dc4f77318ac2232adbb2ebf3ec31f6a8c15a769db5c3b3485","abstract_canon_sha256":"ac69166cf615613f60c0395beadbb8228b32ab2971d6748c5b75facf7d42f6d8"},"schema_version":"1.0"},"canonical_sha256":"b9a08755b8552b7917ff0ee860103f8eccbfe3807b7ee2460660bc343d7930ff","source":{"kind":"arxiv","id":"1311.0701","version":7},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1311.0701","created_at":"2026-05-18T02:57:06Z"},{"alias_kind":"arxiv_version","alias_value":"1311.0701v7","created_at":"2026-05-18T02:57:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1311.0701","created_at":"2026-05-18T02:57:06Z"},{"alias_kind":"pith_short_12","alias_value":"XGQIOVNYKUVX","created_at":"2026-05-18T12:28:06Z"},{"alias_kind":"pith_short_16","alias_value":"XGQIOVNYKUVXSF77","created_at":"2026-05-18T12:28:06Z"},{"alias_kind":"pith_short_8","alias_value":"XGQIOVNY","created_at":"2026-05-18T12:28:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2013:XGQIOVNYKUVXSF77B3UGAEB7R3","target":"record","payload":{"canonical_record":{"source":{"id":"1311.0701","kind":"arxiv","version":7},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2013-11-04T13:56:23Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"8cea681f21554e1dc4f77318ac2232adbb2ebf3ec31f6a8c15a769db5c3b3485","abstract_canon_sha256":"ac69166cf615613f60c0395beadbb8228b32ab2971d6748c5b75facf7d42f6d8"},"schema_version":"1.0"},"canonical_sha256":"b9a08755b8552b7917ff0ee860103f8eccbfe3807b7ee2460660bc343d7930ff","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:57:06.392512Z","signature_b64":"6S0bkH0sX9zA7y0hoqysgSmmPiqFIrkFUSMoJSA6uRJoVTChNqqmeeLjc6SznphJSDGHdATBYXRlHXt15xxTDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9a08755b8552b7917ff0ee860103f8eccbfe3807b7ee2460660bc343d7930ff","last_reissued_at":"2026-05-18T02:57:06.392034Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:57:06.392034Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1311.0701","source_version":7,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:57:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gSUppVYu0FdipRZa1TGUd9XYSHMmQeDK51OME1E5UQmPauW9qLPk/Agz+IDd0ral2VD9NHUk4cILFpgUIXcfAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T21:28:47.836726Z"},"content_sha256":"8e7bdf142a46bf00360534af01cf2d489c5f1564dc665d011a2785e60e1b36f2","schema_version":"1.0","event_id":"sha256:8e7bdf142a46bf00360534af01cf2d489c5f1564dc665d011a2785e60e1b36f2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2013:XGQIOVNYKUVXSF77B3UGAEB7R3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On Fast Dropout and its Applicability to Recurrent Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"stat.ML","authors_text":"Christian Osendorfer, Daniela Korhammer, Justin Bayer, Nutan Chen, Patrick van der Smagt, Sebastian Urban","submitted_at":"2013-11-04T13:56:23Z","abstract_excerpt":"Recurrent Neural Networks (RNNs) are rich models for the processing of sequential data. Recent work on advancing the state of the art has been focused on the optimization or modelling of RNNs, mostly motivated by adressing the problems of the vanishing and exploding gradients. The control of overfitting has seen considerably less attention. This paper contributes to that by analyzing fast dropout, a recent regularization method for generalized linear models and neural networks from a back-propagation inspired perspective. We show that fast dropout implements a quadratic form of an adaptive, pe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1311.0701","kind":"arxiv","version":7},"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":"2026-05-18T02:57:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sOVArZtIbjW1/TqvUo3zoGoMsxgYjAv7PAsxJlgu8oQ4uZYMuPcJuWEQvaz4S1cL3ObdlaKm+WrXMBrGz7hwDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T21:28:47.837397Z"},"content_sha256":"f8cdf42933f07086719954f1ac9e8ceccdc324b984739fd4404e6dbc72a8176e","schema_version":"1.0","event_id":"sha256:f8cdf42933f07086719954f1ac9e8ceccdc324b984739fd4404e6dbc72a8176e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XGQIOVNYKUVXSF77B3UGAEB7R3/bundle.json","state_url":"https://pith.science/pith/XGQIOVNYKUVXSF77B3UGAEB7R3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XGQIOVNYKUVXSF77B3UGAEB7R3/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":"2026-05-25T21:28:47Z","links":{"resolver":"https://pith.science/pith/XGQIOVNYKUVXSF77B3UGAEB7R3","bundle":"https://pith.science/pith/XGQIOVNYKUVXSF77B3UGAEB7R3/bundle.json","state":"https://pith.science/pith/XGQIOVNYKUVXSF77B3UGAEB7R3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XGQIOVNYKUVXSF77B3UGAEB7R3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2013:XGQIOVNYKUVXSF77B3UGAEB7R3","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":"ac69166cf615613f60c0395beadbb8228b32ab2971d6748c5b75facf7d42f6d8","cross_cats_sorted":["cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2013-11-04T13:56:23Z","title_canon_sha256":"8cea681f21554e1dc4f77318ac2232adbb2ebf3ec31f6a8c15a769db5c3b3485"},"schema_version":"1.0","source":{"id":"1311.0701","kind":"arxiv","version":7}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1311.0701","created_at":"2026-05-18T02:57:06Z"},{"alias_kind":"arxiv_version","alias_value":"1311.0701v7","created_at":"2026-05-18T02:57:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1311.0701","created_at":"2026-05-18T02:57:06Z"},{"alias_kind":"pith_short_12","alias_value":"XGQIOVNYKUVX","created_at":"2026-05-18T12:28:06Z"},{"alias_kind":"pith_short_16","alias_value":"XGQIOVNYKUVXSF77","created_at":"2026-05-18T12:28:06Z"},{"alias_kind":"pith_short_8","alias_value":"XGQIOVNY","created_at":"2026-05-18T12:28:06Z"}],"graph_snapshots":[{"event_id":"sha256:f8cdf42933f07086719954f1ac9e8ceccdc324b984739fd4404e6dbc72a8176e","target":"graph","created_at":"2026-05-18T02:57:06Z","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":"Recurrent Neural Networks (RNNs) are rich models for the processing of sequential data. Recent work on advancing the state of the art has been focused on the optimization or modelling of RNNs, mostly motivated by adressing the problems of the vanishing and exploding gradients. The control of overfitting has seen considerably less attention. This paper contributes to that by analyzing fast dropout, a recent regularization method for generalized linear models and neural networks from a back-propagation inspired perspective. We show that fast dropout implements a quadratic form of an adaptive, pe","authors_text":"Christian Osendorfer, Daniela Korhammer, Justin Bayer, Nutan Chen, Patrick van der Smagt, Sebastian Urban","cross_cats":["cs.LG","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2013-11-04T13:56:23Z","title":"On Fast Dropout and its Applicability to Recurrent Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1311.0701","kind":"arxiv","version":7},"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":"sha256:8e7bdf142a46bf00360534af01cf2d489c5f1564dc665d011a2785e60e1b36f2","target":"record","created_at":"2026-05-18T02:57:06Z","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":"ac69166cf615613f60c0395beadbb8228b32ab2971d6748c5b75facf7d42f6d8","cross_cats_sorted":["cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2013-11-04T13:56:23Z","title_canon_sha256":"8cea681f21554e1dc4f77318ac2232adbb2ebf3ec31f6a8c15a769db5c3b3485"},"schema_version":"1.0","source":{"id":"1311.0701","kind":"arxiv","version":7}},"canonical_sha256":"b9a08755b8552b7917ff0ee860103f8eccbfe3807b7ee2460660bc343d7930ff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b9a08755b8552b7917ff0ee860103f8eccbfe3807b7ee2460660bc343d7930ff","first_computed_at":"2026-05-18T02:57:06.392034Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:57:06.392034Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6S0bkH0sX9zA7y0hoqysgSmmPiqFIrkFUSMoJSA6uRJoVTChNqqmeeLjc6SznphJSDGHdATBYXRlHXt15xxTDA==","signature_status":"signed_v1","signed_at":"2026-05-18T02:57:06.392512Z","signed_message":"canonical_sha256_bytes"},"source_id":"1311.0701","source_kind":"arxiv","source_version":7}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8e7bdf142a46bf00360534af01cf2d489c5f1564dc665d011a2785e60e1b36f2","sha256:f8cdf42933f07086719954f1ac9e8ceccdc324b984739fd4404e6dbc72a8176e"],"state_sha256":"99f09b3b91557a8b7a66f18c81802999147208a46e8a6029728ce47ccb15a748"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vTfZY5BQHHfjDgM/5qTP68agyhQK1yfOB7IYN3YTmVJHz27Vr8JMpgY1do0Z3yiHFaouSlp3MIWVL1rEWSiZDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T21:28:47.841355Z","bundle_sha256":"4eca2e16a649bed4660f4e12468a7fb419cecdcbca84addf12e5868adf340176"}}