{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:AKC6HV6J5X6KPUFG3CQ7MQKYNL","short_pith_number":"pith:AKC6HV6J","canonical_record":{"source":{"id":"1405.1380","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2014-05-06T17:41:33Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"dd26ce324a5df812b64b00778976841ddffc5374ce1ad7b7effdfaf504c7657f","abstract_canon_sha256":"66bae187495bcabad94694fa1fa860c8529d3c20e9ee7e6cee8ffe4368439157"},"schema_version":"1.0"},"canonical_sha256":"0285e3d7c9edfca7d0a6d8a1f641586afa11403357b2244946a6098ba63f7e2d","source":{"kind":"arxiv","id":"1405.1380","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1405.1380","created_at":"2026-05-18T01:48:06Z"},{"alias_kind":"arxiv_version","alias_value":"1405.1380v4","created_at":"2026-05-18T01:48:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1405.1380","created_at":"2026-05-18T01:48:06Z"},{"alias_kind":"pith_short_12","alias_value":"AKC6HV6J5X6K","created_at":"2026-05-18T12:28:19Z"},{"alias_kind":"pith_short_16","alias_value":"AKC6HV6J5X6KPUFG","created_at":"2026-05-18T12:28:19Z"},{"alias_kind":"pith_short_8","alias_value":"AKC6HV6J","created_at":"2026-05-18T12:28:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:AKC6HV6J5X6KPUFG3CQ7MQKYNL","target":"record","payload":{"canonical_record":{"source":{"id":"1405.1380","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2014-05-06T17:41:33Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"dd26ce324a5df812b64b00778976841ddffc5374ce1ad7b7effdfaf504c7657f","abstract_canon_sha256":"66bae187495bcabad94694fa1fa860c8529d3c20e9ee7e6cee8ffe4368439157"},"schema_version":"1.0"},"canonical_sha256":"0285e3d7c9edfca7d0a6d8a1f641586afa11403357b2244946a6098ba63f7e2d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:48:06.812540Z","signature_b64":"GVJYG+mz0+Tz6PlDATDRm2lyRLpfXwLoX6KLk08DqH5gVzYXoO2bCXCgFfpmCoLsYufX9KP06E3CQcZA+iWnCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0285e3d7c9edfca7d0a6d8a1f641586afa11403357b2244946a6098ba63f7e2d","last_reissued_at":"2026-05-18T01:48:06.811580Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:48:06.811580Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1405.1380","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":"2026-05-18T01:48:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Us9IAr/56RiRsD4oCaf87D4HL7oByc6vo7NKnjB9BYRWxktsPW/lUeK/vJBBvp2ZSY6ctLIf0/29cX0bvMLUDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T02:59:18.529518Z"},"content_sha256":"eb5e5f83553918df36b62f3f8da7e44efd5bf03085fd3ed610a41a829803a33e","schema_version":"1.0","event_id":"sha256:eb5e5f83553918df36b62f3f8da7e44efd5bf03085fd3ed610a41a829803a33e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:AKC6HV6J5X6KPUFG3CQ7MQKYNL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Is Joint Training Better for Deep Auto-Encoders?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"stat.ML","authors_text":"Devansh Arpit, Ifeoma Nwogu, Venu Govindaraju, Yingbo Zhou","submitted_at":"2014-05-06T17:41:33Z","abstract_excerpt":"Traditionally, when generative models of data are developed via deep architectures, greedy layer-wise pre-training is employed. In a well-trained model, the lower layer of the architecture models the data distribution conditional upon the hidden variables, while the higher layers model the hidden distribution prior. But due to the greedy scheme of the layerwise training technique, the parameters of lower layers are fixed when training higher layers. This makes it extremely challenging for the model to learn the hidden distribution prior, which in turn leads to a suboptimal model for the data d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1405.1380","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":"2026-05-18T01:48:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LlzTHPWOYW9Ulhc8iwvPStTavTjuQV7gQtNTUek97HK+qr/oCnSVwExQui2J0k52/jaHV97eyJnTmokRQadEBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T02:59:18.530133Z"},"content_sha256":"337244e2464c73d069bb22288b6cb3f0ae3b34110690833645df242b606361af","schema_version":"1.0","event_id":"sha256:337244e2464c73d069bb22288b6cb3f0ae3b34110690833645df242b606361af"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AKC6HV6J5X6KPUFG3CQ7MQKYNL/bundle.json","state_url":"https://pith.science/pith/AKC6HV6J5X6KPUFG3CQ7MQKYNL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AKC6HV6J5X6KPUFG3CQ7MQKYNL/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":"2026-06-08T02:59:18Z","links":{"resolver":"https://pith.science/pith/AKC6HV6J5X6KPUFG3CQ7MQKYNL","bundle":"https://pith.science/pith/AKC6HV6J5X6KPUFG3CQ7MQKYNL/bundle.json","state":"https://pith.science/pith/AKC6HV6J5X6KPUFG3CQ7MQKYNL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AKC6HV6J5X6KPUFG3CQ7MQKYNL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:AKC6HV6J5X6KPUFG3CQ7MQKYNL","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":"66bae187495bcabad94694fa1fa860c8529d3c20e9ee7e6cee8ffe4368439157","cross_cats_sorted":["cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2014-05-06T17:41:33Z","title_canon_sha256":"dd26ce324a5df812b64b00778976841ddffc5374ce1ad7b7effdfaf504c7657f"},"schema_version":"1.0","source":{"id":"1405.1380","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1405.1380","created_at":"2026-05-18T01:48:06Z"},{"alias_kind":"arxiv_version","alias_value":"1405.1380v4","created_at":"2026-05-18T01:48:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1405.1380","created_at":"2026-05-18T01:48:06Z"},{"alias_kind":"pith_short_12","alias_value":"AKC6HV6J5X6K","created_at":"2026-05-18T12:28:19Z"},{"alias_kind":"pith_short_16","alias_value":"AKC6HV6J5X6KPUFG","created_at":"2026-05-18T12:28:19Z"},{"alias_kind":"pith_short_8","alias_value":"AKC6HV6J","created_at":"2026-05-18T12:28:19Z"}],"graph_snapshots":[{"event_id":"sha256:337244e2464c73d069bb22288b6cb3f0ae3b34110690833645df242b606361af","target":"graph","created_at":"2026-05-18T01:48:06Z","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":"Traditionally, when generative models of data are developed via deep architectures, greedy layer-wise pre-training is employed. In a well-trained model, the lower layer of the architecture models the data distribution conditional upon the hidden variables, while the higher layers model the hidden distribution prior. But due to the greedy scheme of the layerwise training technique, the parameters of lower layers are fixed when training higher layers. This makes it extremely challenging for the model to learn the hidden distribution prior, which in turn leads to a suboptimal model for the data d","authors_text":"Devansh Arpit, Ifeoma Nwogu, Venu Govindaraju, Yingbo Zhou","cross_cats":["cs.LG","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2014-05-06T17:41:33Z","title":"Is Joint Training Better for Deep Auto-Encoders?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1405.1380","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:eb5e5f83553918df36b62f3f8da7e44efd5bf03085fd3ed610a41a829803a33e","target":"record","created_at":"2026-05-18T01:48:06Z","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":"66bae187495bcabad94694fa1fa860c8529d3c20e9ee7e6cee8ffe4368439157","cross_cats_sorted":["cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2014-05-06T17:41:33Z","title_canon_sha256":"dd26ce324a5df812b64b00778976841ddffc5374ce1ad7b7effdfaf504c7657f"},"schema_version":"1.0","source":{"id":"1405.1380","kind":"arxiv","version":4}},"canonical_sha256":"0285e3d7c9edfca7d0a6d8a1f641586afa11403357b2244946a6098ba63f7e2d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0285e3d7c9edfca7d0a6d8a1f641586afa11403357b2244946a6098ba63f7e2d","first_computed_at":"2026-05-18T01:48:06.811580Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:48:06.811580Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GVJYG+mz0+Tz6PlDATDRm2lyRLpfXwLoX6KLk08DqH5gVzYXoO2bCXCgFfpmCoLsYufX9KP06E3CQcZA+iWnCg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:48:06.812540Z","signed_message":"canonical_sha256_bytes"},"source_id":"1405.1380","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eb5e5f83553918df36b62f3f8da7e44efd5bf03085fd3ed610a41a829803a33e","sha256:337244e2464c73d069bb22288b6cb3f0ae3b34110690833645df242b606361af"],"state_sha256":"89477e380410f341c57b9fdb3421d4f439a63bf8d7881d2b468930fe7b46a509"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+sIga+snDwVd7sMfaKJSWnwFPmJOCL0J8DQzHxXwgj3y+7oKQNtenJu4aAWnHEtAu4nUsPVRzd0Wep+9LSmMAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T02:59:18.533376Z","bundle_sha256":"e07a08ee03e5a90c932db1b64f0026c3335b788cab8579bc880df8a59b76dcd6"}}