{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:J2E6VPE26QTZ4MY5S7UIPFZKNP","short_pith_number":"pith:J2E6VPE2","canonical_record":{"source":{"id":"1602.02282","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-02-06T17:32:48Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3a4f4e8b859a574befb760243922acd4d2162855b6fe746434acea52e5ad9802","abstract_canon_sha256":"a7106a0868f939e01aef20613daf6d3827a574f4411fe8e7dec9af990bff642f"},"schema_version":"1.0"},"canonical_sha256":"4e89eabc9af4279e331d97e887972a6bce3e1bc1c08c73e84aafba6ce560cbf1","source":{"kind":"arxiv","id":"1602.02282","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1602.02282","created_at":"2026-05-18T01:13:30Z"},{"alias_kind":"arxiv_version","alias_value":"1602.02282v3","created_at":"2026-05-18T01:13:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.02282","created_at":"2026-05-18T01:13:30Z"},{"alias_kind":"pith_short_12","alias_value":"J2E6VPE26QTZ","created_at":"2026-05-18T12:30:22Z"},{"alias_kind":"pith_short_16","alias_value":"J2E6VPE26QTZ4MY5","created_at":"2026-05-18T12:30:22Z"},{"alias_kind":"pith_short_8","alias_value":"J2E6VPE2","created_at":"2026-05-18T12:30:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:J2E6VPE26QTZ4MY5S7UIPFZKNP","target":"record","payload":{"canonical_record":{"source":{"id":"1602.02282","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-02-06T17:32:48Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3a4f4e8b859a574befb760243922acd4d2162855b6fe746434acea52e5ad9802","abstract_canon_sha256":"a7106a0868f939e01aef20613daf6d3827a574f4411fe8e7dec9af990bff642f"},"schema_version":"1.0"},"canonical_sha256":"4e89eabc9af4279e331d97e887972a6bce3e1bc1c08c73e84aafba6ce560cbf1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:13:30.501803Z","signature_b64":"Y7Wz0Eb32AsW1K9IJ8EFORxt/TZBw02AhG4i6rs04nDdnbi1ZOcNd4Sx/f3VrXtjdqVbfPcQ56g+Xtlm0TaaDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4e89eabc9af4279e331d97e887972a6bce3e1bc1c08c73e84aafba6ce560cbf1","last_reissued_at":"2026-05-18T01:13:30.501206Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:13:30.501206Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1602.02282","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:13:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TX3b1bQrkY3NHmRtLRqWkgEHSjJbNHN2B8ok/RLEmgdYnSJUuvAKMcy1ucpImrC9105SA5HleW6RYhXygkKQAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T06:14:09.860842Z"},"content_sha256":"a7e98cbf46e27db4e93514cfc063281f69b98c7ec47d5427d4f3e5e55a06d75d","schema_version":"1.0","event_id":"sha256:a7e98cbf46e27db4e93514cfc063281f69b98c7ec47d5427d4f3e5e55a06d75d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:J2E6VPE26QTZ4MY5S7UIPFZKNP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Ladder Variational Autoencoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Casper Kaae S{\\o}nderby, Lars Maal{\\o}e, Ole Winther, S{\\o}ren Kaae S{\\o}nderby, Tapani Raiko","submitted_at":"2016-02-06T17:32:48Z","abstract_excerpt":"Variational Autoencoders are powerful models for unsupervised learning. However deep models with several layers of dependent stochastic variables are difficult to train which limits the improvements obtained using these highly expressive models. We propose a new inference model, the Ladder Variational Autoencoder, that recursively corrects the generative distribution by a data dependent approximate likelihood in a process resembling the recently proposed Ladder Network. We show that this model provides state of the art predictive log-likelihood and tighter log-likelihood lower bound compared t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.02282","kind":"arxiv","version":3},"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":"2026-05-18T01:13:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"urPnYBA06FG4pr01/6UmaGN6VvnRkvmAdpbqpzbiMqbyvpr5ERDunGpfY4k3jYz4rgnvrSn1Lp3Rwc4asm4pDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T06:14:09.861428Z"},"content_sha256":"d6fa9cb3dfa774b9ced9bf445419362fa96e0aa01516893949b141b4acfa230a","schema_version":"1.0","event_id":"sha256:d6fa9cb3dfa774b9ced9bf445419362fa96e0aa01516893949b141b4acfa230a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/J2E6VPE26QTZ4MY5S7UIPFZKNP/bundle.json","state_url":"https://pith.science/pith/J2E6VPE26QTZ4MY5S7UIPFZKNP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/J2E6VPE26QTZ4MY5S7UIPFZKNP/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":"2026-06-07T06:14:09Z","links":{"resolver":"https://pith.science/pith/J2E6VPE26QTZ4MY5S7UIPFZKNP","bundle":"https://pith.science/pith/J2E6VPE26QTZ4MY5S7UIPFZKNP/bundle.json","state":"https://pith.science/pith/J2E6VPE26QTZ4MY5S7UIPFZKNP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/J2E6VPE26QTZ4MY5S7UIPFZKNP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:J2E6VPE26QTZ4MY5S7UIPFZKNP","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":"a7106a0868f939e01aef20613daf6d3827a574f4411fe8e7dec9af990bff642f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-02-06T17:32:48Z","title_canon_sha256":"3a4f4e8b859a574befb760243922acd4d2162855b6fe746434acea52e5ad9802"},"schema_version":"1.0","source":{"id":"1602.02282","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1602.02282","created_at":"2026-05-18T01:13:30Z"},{"alias_kind":"arxiv_version","alias_value":"1602.02282v3","created_at":"2026-05-18T01:13:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.02282","created_at":"2026-05-18T01:13:30Z"},{"alias_kind":"pith_short_12","alias_value":"J2E6VPE26QTZ","created_at":"2026-05-18T12:30:22Z"},{"alias_kind":"pith_short_16","alias_value":"J2E6VPE26QTZ4MY5","created_at":"2026-05-18T12:30:22Z"},{"alias_kind":"pith_short_8","alias_value":"J2E6VPE2","created_at":"2026-05-18T12:30:22Z"}],"graph_snapshots":[{"event_id":"sha256:d6fa9cb3dfa774b9ced9bf445419362fa96e0aa01516893949b141b4acfa230a","target":"graph","created_at":"2026-05-18T01:13:30Z","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":"Variational Autoencoders are powerful models for unsupervised learning. However deep models with several layers of dependent stochastic variables are difficult to train which limits the improvements obtained using these highly expressive models. We propose a new inference model, the Ladder Variational Autoencoder, that recursively corrects the generative distribution by a data dependent approximate likelihood in a process resembling the recently proposed Ladder Network. We show that this model provides state of the art predictive log-likelihood and tighter log-likelihood lower bound compared t","authors_text":"Casper Kaae S{\\o}nderby, Lars Maal{\\o}e, Ole Winther, S{\\o}ren Kaae S{\\o}nderby, Tapani Raiko","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-02-06T17:32:48Z","title":"Ladder Variational Autoencoders"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.02282","kind":"arxiv","version":3},"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:a7e98cbf46e27db4e93514cfc063281f69b98c7ec47d5427d4f3e5e55a06d75d","target":"record","created_at":"2026-05-18T01:13:30Z","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":"a7106a0868f939e01aef20613daf6d3827a574f4411fe8e7dec9af990bff642f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-02-06T17:32:48Z","title_canon_sha256":"3a4f4e8b859a574befb760243922acd4d2162855b6fe746434acea52e5ad9802"},"schema_version":"1.0","source":{"id":"1602.02282","kind":"arxiv","version":3}},"canonical_sha256":"4e89eabc9af4279e331d97e887972a6bce3e1bc1c08c73e84aafba6ce560cbf1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4e89eabc9af4279e331d97e887972a6bce3e1bc1c08c73e84aafba6ce560cbf1","first_computed_at":"2026-05-18T01:13:30.501206Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:13:30.501206Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Y7Wz0Eb32AsW1K9IJ8EFORxt/TZBw02AhG4i6rs04nDdnbi1ZOcNd4Sx/f3VrXtjdqVbfPcQ56g+Xtlm0TaaDA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:13:30.501803Z","signed_message":"canonical_sha256_bytes"},"source_id":"1602.02282","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a7e98cbf46e27db4e93514cfc063281f69b98c7ec47d5427d4f3e5e55a06d75d","sha256:d6fa9cb3dfa774b9ced9bf445419362fa96e0aa01516893949b141b4acfa230a"],"state_sha256":"b980aab3ae567af818a02acc81a1cf656bc6751fb666f8d06042726ee22803e3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rTxcMz6yJJ7WMqa/GwmMWIgwwZrhOiwQMsM14fC6ecJEE0zZaPeOcw2mzcI4Sq0qmIfyAJb0ZgzD03rV4VcrBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T06:14:09.864430Z","bundle_sha256":"a9e4f7f18e7e79074b989f4b42c7d1ceef9864d3ed4b9aac3b25157fcd07a80f"}}