{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:FBJUHAXQMU6TVZLHT5Q3DKEWT6","short_pith_number":"pith:FBJUHAXQ","canonical_record":{"source":{"id":"1402.0915","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2014-02-05T00:41:58Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6d7921c0b0c995a6279d1b2b704b50a2e6c6e1d48610d78396f553691289c5ae","abstract_canon_sha256":"2ece64da7119a5ea51b2cae621485f48ec1626998d89814228d6cedb1298cb94"},"schema_version":"1.0"},"canonical_sha256":"28534382f0653d3ae5679f61b1a8969f83e3f082030b978911913f05f619db75","source":{"kind":"arxiv","id":"1402.0915","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1402.0915","created_at":"2026-05-18T03:00:02Z"},{"alias_kind":"arxiv_version","alias_value":"1402.0915v1","created_at":"2026-05-18T03:00:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1402.0915","created_at":"2026-05-18T03:00:02Z"},{"alias_kind":"pith_short_12","alias_value":"FBJUHAXQMU6T","created_at":"2026-05-18T12:28:28Z"},{"alias_kind":"pith_short_16","alias_value":"FBJUHAXQMU6TVZLH","created_at":"2026-05-18T12:28:28Z"},{"alias_kind":"pith_short_8","alias_value":"FBJUHAXQ","created_at":"2026-05-18T12:28:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:FBJUHAXQMU6TVZLHT5Q3DKEWT6","target":"record","payload":{"canonical_record":{"source":{"id":"1402.0915","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2014-02-05T00:41:58Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6d7921c0b0c995a6279d1b2b704b50a2e6c6e1d48610d78396f553691289c5ae","abstract_canon_sha256":"2ece64da7119a5ea51b2cae621485f48ec1626998d89814228d6cedb1298cb94"},"schema_version":"1.0"},"canonical_sha256":"28534382f0653d3ae5679f61b1a8969f83e3f082030b978911913f05f619db75","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:00:02.333122Z","signature_b64":"ewwAIxBkOgaeztvL4CkaY7AVk4xqBhBbALRMOV++MYExclvOWuv9nZuJzIn7xEft3cdalnv2GtqNu6g71pmjBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28534382f0653d3ae5679f61b1a8969f83e3f082030b978911913f05f619db75","last_reissued_at":"2026-05-18T03:00:02.332451Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:00:02.332451Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1402.0915","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":"2026-05-18T03:00:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6E2+xAl2pAJgXkn/j3iQrCX3XbHtWzD6TORr3jxudJNXmOU4hGL0oWB6gDo4IRT1yEuToljOXuYxvxg19gxmCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T18:48:50.715898Z"},"content_sha256":"744bd25f64b52e5d86557828eddec40903f5a0d6b5b5235fecdf7f2a98f2724c","schema_version":"1.0","event_id":"sha256:744bd25f64b52e5d86557828eddec40903f5a0d6b5b5235fecdf7f2a98f2724c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:FBJUHAXQMU6TVZLHT5Q3DKEWT6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Ordered Representations with Nested Dropout","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Michael A. Gelbart, Oren Rippel, Ryan P. Adams","submitted_at":"2014-02-05T00:41:58Z","abstract_excerpt":"In this paper, we study ordered representations of data in which different dimensions have different degrees of importance. To learn these representations we introduce nested dropout, a procedure for stochastically removing coherent nested sets of hidden units in a neural network. We first present a sequence of theoretical results in the simple case of a semi-linear autoencoder. We rigorously show that the application of nested dropout enforces identifiability of the units, which leads to an exact equivalence with PCA. We then extend the algorithm to deep models and demonstrate the relevance o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1402.0915","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":"2026-05-18T03:00:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9G3nykpFt32YcVVf4wLECB/Hh5mUfFeWJTiLr1pGhnH2GhJdqaeKZVdIES/GqiXvq7DY95KoVV3xle2xwi5MAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T18:48:50.717683Z"},"content_sha256":"167b9c92c6793426fa289dad8525e18f4dacd1b16326e376ad266c3ba483e8e2","schema_version":"1.0","event_id":"sha256:167b9c92c6793426fa289dad8525e18f4dacd1b16326e376ad266c3ba483e8e2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FBJUHAXQMU6TVZLHT5Q3DKEWT6/bundle.json","state_url":"https://pith.science/pith/FBJUHAXQMU6TVZLHT5Q3DKEWT6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FBJUHAXQMU6TVZLHT5Q3DKEWT6/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":"2026-08-18T18:48:50Z","links":{"resolver":"https://pith.science/pith/FBJUHAXQMU6TVZLHT5Q3DKEWT6","bundle":"https://pith.science/pith/FBJUHAXQMU6TVZLHT5Q3DKEWT6/bundle.json","state":"https://pith.science/pith/FBJUHAXQMU6TVZLHT5Q3DKEWT6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FBJUHAXQMU6TVZLHT5Q3DKEWT6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:FBJUHAXQMU6TVZLHT5Q3DKEWT6","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":"2ece64da7119a5ea51b2cae621485f48ec1626998d89814228d6cedb1298cb94","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2014-02-05T00:41:58Z","title_canon_sha256":"6d7921c0b0c995a6279d1b2b704b50a2e6c6e1d48610d78396f553691289c5ae"},"schema_version":"1.0","source":{"id":"1402.0915","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1402.0915","created_at":"2026-05-18T03:00:02Z"},{"alias_kind":"arxiv_version","alias_value":"1402.0915v1","created_at":"2026-05-18T03:00:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1402.0915","created_at":"2026-05-18T03:00:02Z"},{"alias_kind":"pith_short_12","alias_value":"FBJUHAXQMU6T","created_at":"2026-05-18T12:28:28Z"},{"alias_kind":"pith_short_16","alias_value":"FBJUHAXQMU6TVZLH","created_at":"2026-05-18T12:28:28Z"},{"alias_kind":"pith_short_8","alias_value":"FBJUHAXQ","created_at":"2026-05-18T12:28:28Z"}],"graph_snapshots":[{"event_id":"sha256:167b9c92c6793426fa289dad8525e18f4dacd1b16326e376ad266c3ba483e8e2","target":"graph","created_at":"2026-05-18T03:00:02Z","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":"In this paper, we study ordered representations of data in which different dimensions have different degrees of importance. To learn these representations we introduce nested dropout, a procedure for stochastically removing coherent nested sets of hidden units in a neural network. We first present a sequence of theoretical results in the simple case of a semi-linear autoencoder. We rigorously show that the application of nested dropout enforces identifiability of the units, which leads to an exact equivalence with PCA. We then extend the algorithm to deep models and demonstrate the relevance o","authors_text":"Michael A. Gelbart, Oren Rippel, Ryan P. Adams","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2014-02-05T00:41:58Z","title":"Learning Ordered Representations with Nested Dropout"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1402.0915","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":"sha256:744bd25f64b52e5d86557828eddec40903f5a0d6b5b5235fecdf7f2a98f2724c","target":"record","created_at":"2026-05-18T03:00:02Z","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":"2ece64da7119a5ea51b2cae621485f48ec1626998d89814228d6cedb1298cb94","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2014-02-05T00:41:58Z","title_canon_sha256":"6d7921c0b0c995a6279d1b2b704b50a2e6c6e1d48610d78396f553691289c5ae"},"schema_version":"1.0","source":{"id":"1402.0915","kind":"arxiv","version":1}},"canonical_sha256":"28534382f0653d3ae5679f61b1a8969f83e3f082030b978911913f05f619db75","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"28534382f0653d3ae5679f61b1a8969f83e3f082030b978911913f05f619db75","first_computed_at":"2026-05-18T03:00:02.332451Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:00:02.332451Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ewwAIxBkOgaeztvL4CkaY7AVk4xqBhBbALRMOV++MYExclvOWuv9nZuJzIn7xEft3cdalnv2GtqNu6g71pmjBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T03:00:02.333122Z","signed_message":"canonical_sha256_bytes"},"source_id":"1402.0915","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:744bd25f64b52e5d86557828eddec40903f5a0d6b5b5235fecdf7f2a98f2724c","sha256:167b9c92c6793426fa289dad8525e18f4dacd1b16326e376ad266c3ba483e8e2"],"state_sha256":"80ddd0716207e8a14d55304494df504db6b04fc2b53bf78950a58d78f3d1e0fd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lU4COLB8Jw9R3o3v9QppBdtL6x8JrTqYYTWSpVG21OB0LNzTASTB9fT1Vv1ToiesS4GOZQp9Cc0IXK70ObISAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T18:48:50.723206Z","bundle_sha256":"fb9cefedc85e75dc857703f660ee4b562dedbaeda26f412fe3b19e03afc9f97b"}}