{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:FOSBWB5BZYVAGA7OIKVGZPBGSW","short_pith_number":"pith:FOSBWB5B","canonical_record":{"source":{"id":"1407.3289","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2014-07-11T20:32:34Z","cross_cats_sorted":["cs.LG","math.ST","stat.TH"],"title_canon_sha256":"3a89b71605d1c8aee535c6179b981de7c028cb54aab40d9607e9c71932df7bdc","abstract_canon_sha256":"1b3aebe0f7462b3b25e59c1b4d5a5562605b0d12364aa5ff5e14aa9f00cd1984"},"schema_version":"1.0"},"canonical_sha256":"2ba41b07a1ce2a0303ee42aa6cbc2695b004ea2807058cb80c6aa1d1faccd042","source":{"kind":"arxiv","id":"1407.3289","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1407.3289","created_at":"2026-05-18T02:38:59Z"},{"alias_kind":"arxiv_version","alias_value":"1407.3289v2","created_at":"2026-05-18T02:38:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1407.3289","created_at":"2026-05-18T02:38:59Z"},{"alias_kind":"pith_short_12","alias_value":"FOSBWB5BZYVA","created_at":"2026-05-18T12:28:28Z"},{"alias_kind":"pith_short_16","alias_value":"FOSBWB5BZYVAGA7O","created_at":"2026-05-18T12:28:28Z"},{"alias_kind":"pith_short_8","alias_value":"FOSBWB5B","created_at":"2026-05-18T12:28:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:FOSBWB5BZYVAGA7OIKVGZPBGSW","target":"record","payload":{"canonical_record":{"source":{"id":"1407.3289","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2014-07-11T20:32:34Z","cross_cats_sorted":["cs.LG","math.ST","stat.TH"],"title_canon_sha256":"3a89b71605d1c8aee535c6179b981de7c028cb54aab40d9607e9c71932df7bdc","abstract_canon_sha256":"1b3aebe0f7462b3b25e59c1b4d5a5562605b0d12364aa5ff5e14aa9f00cd1984"},"schema_version":"1.0"},"canonical_sha256":"2ba41b07a1ce2a0303ee42aa6cbc2695b004ea2807058cb80c6aa1d1faccd042","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:38:59.280884Z","signature_b64":"a5WuDaWFKkpeCq2QB9DWx3TILC6y5IFjnFzcRzLPpLWhf6JeyZ75oC4S4lkA6q3jIZ/C2B0+rnoIZPALsgj+Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ba41b07a1ce2a0303ee42aa6cbc2695b004ea2807058cb80c6aa1d1faccd042","last_reissued_at":"2026-05-18T02:38:59.280359Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:38:59.280359Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1407.3289","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:38:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QKcrnC8ke8ZJl+lsYoEYWpC5EESGraEL3c2nT/3YpquQC0GtL1ZVq1Ewi1mYQyyPGgcSPkFP2MNrtifRuCkLCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T12:22:14.090738Z"},"content_sha256":"c8ca9b2e6542325a4b667b711f85bbd7157e16a8fa02f23f0653e645967678e2","schema_version":"1.0","event_id":"sha256:c8ca9b2e6542325a4b667b711f85bbd7157e16a8fa02f23f0653e645967678e2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:FOSBWB5BZYVAGA7OIKVGZPBGSW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Altitude Training: Strong Bounds for Single-Layer Dropout","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Percy Liang, Sida Wang, Stefan Wager, William Fithian","submitted_at":"2014-07-11T20:32:34Z","abstract_excerpt":"Dropout training, originally designed for deep neural networks, has been successful on high-dimensional single-layer natural language tasks. This paper proposes a theoretical explanation for this phenomenon: we show that, under a generative Poisson topic model with long documents, dropout training improves the exponent in the generalization bound for empirical risk minimization. Dropout achieves this gain much like a marathon runner who practices at altitude: once a classifier learns to perform reasonably well on training examples that have been artificially corrupted by dropout, it will do ve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1407.3289","kind":"arxiv","version":2},"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":"2026-05-18T02:38:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9loXg1bB8pgpj5l6Ez8/OaLT7HL71WK9123dbG7J0CNmJEKKM9DJzTRTulVl7lfSwq5GEThT2ASLik+0k8snAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T12:22:14.091402Z"},"content_sha256":"070cc7693d986c5d2336242049454e26c4fa064172b43e212c8481e26ed24205","schema_version":"1.0","event_id":"sha256:070cc7693d986c5d2336242049454e26c4fa064172b43e212c8481e26ed24205"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FOSBWB5BZYVAGA7OIKVGZPBGSW/bundle.json","state_url":"https://pith.science/pith/FOSBWB5BZYVAGA7OIKVGZPBGSW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FOSBWB5BZYVAGA7OIKVGZPBGSW/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":"2026-05-25T12:22:14Z","links":{"resolver":"https://pith.science/pith/FOSBWB5BZYVAGA7OIKVGZPBGSW","bundle":"https://pith.science/pith/FOSBWB5BZYVAGA7OIKVGZPBGSW/bundle.json","state":"https://pith.science/pith/FOSBWB5BZYVAGA7OIKVGZPBGSW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FOSBWB5BZYVAGA7OIKVGZPBGSW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:FOSBWB5BZYVAGA7OIKVGZPBGSW","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":"1b3aebe0f7462b3b25e59c1b4d5a5562605b0d12364aa5ff5e14aa9f00cd1984","cross_cats_sorted":["cs.LG","math.ST","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2014-07-11T20:32:34Z","title_canon_sha256":"3a89b71605d1c8aee535c6179b981de7c028cb54aab40d9607e9c71932df7bdc"},"schema_version":"1.0","source":{"id":"1407.3289","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1407.3289","created_at":"2026-05-18T02:38:59Z"},{"alias_kind":"arxiv_version","alias_value":"1407.3289v2","created_at":"2026-05-18T02:38:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1407.3289","created_at":"2026-05-18T02:38:59Z"},{"alias_kind":"pith_short_12","alias_value":"FOSBWB5BZYVA","created_at":"2026-05-18T12:28:28Z"},{"alias_kind":"pith_short_16","alias_value":"FOSBWB5BZYVAGA7O","created_at":"2026-05-18T12:28:28Z"},{"alias_kind":"pith_short_8","alias_value":"FOSBWB5B","created_at":"2026-05-18T12:28:28Z"}],"graph_snapshots":[{"event_id":"sha256:070cc7693d986c5d2336242049454e26c4fa064172b43e212c8481e26ed24205","target":"graph","created_at":"2026-05-18T02:38:59Z","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 training, originally designed for deep neural networks, has been successful on high-dimensional single-layer natural language tasks. This paper proposes a theoretical explanation for this phenomenon: we show that, under a generative Poisson topic model with long documents, dropout training improves the exponent in the generalization bound for empirical risk minimization. Dropout achieves this gain much like a marathon runner who practices at altitude: once a classifier learns to perform reasonably well on training examples that have been artificially corrupted by dropout, it will do ve","authors_text":"Percy Liang, Sida Wang, Stefan Wager, William Fithian","cross_cats":["cs.LG","math.ST","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2014-07-11T20:32:34Z","title":"Altitude Training: Strong Bounds for Single-Layer Dropout"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1407.3289","kind":"arxiv","version":2},"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:c8ca9b2e6542325a4b667b711f85bbd7157e16a8fa02f23f0653e645967678e2","target":"record","created_at":"2026-05-18T02:38:59Z","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":"1b3aebe0f7462b3b25e59c1b4d5a5562605b0d12364aa5ff5e14aa9f00cd1984","cross_cats_sorted":["cs.LG","math.ST","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2014-07-11T20:32:34Z","title_canon_sha256":"3a89b71605d1c8aee535c6179b981de7c028cb54aab40d9607e9c71932df7bdc"},"schema_version":"1.0","source":{"id":"1407.3289","kind":"arxiv","version":2}},"canonical_sha256":"2ba41b07a1ce2a0303ee42aa6cbc2695b004ea2807058cb80c6aa1d1faccd042","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2ba41b07a1ce2a0303ee42aa6cbc2695b004ea2807058cb80c6aa1d1faccd042","first_computed_at":"2026-05-18T02:38:59.280359Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:38:59.280359Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"a5WuDaWFKkpeCq2QB9DWx3TILC6y5IFjnFzcRzLPpLWhf6JeyZ75oC4S4lkA6q3jIZ/C2B0+rnoIZPALsgj+Cg==","signature_status":"signed_v1","signed_at":"2026-05-18T02:38:59.280884Z","signed_message":"canonical_sha256_bytes"},"source_id":"1407.3289","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c8ca9b2e6542325a4b667b711f85bbd7157e16a8fa02f23f0653e645967678e2","sha256:070cc7693d986c5d2336242049454e26c4fa064172b43e212c8481e26ed24205"],"state_sha256":"dc1da1268b83567ee3482ecd732464120b4e8292c786e1fd48c64bbdd658ac1d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3M26j2HTCT/I0SjHWBHYtczbBpITLX72//WdCrEkYh0r3c7ZcWUFZugWGJS3FqLbhLqwAkPw6Pel4O4mibi5AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T12:22:14.094826Z","bundle_sha256":"788f70977ea5af5cab98ecb03aeef9f989efab645514bb46ab1dbb48302b3781"}}