{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2012:S4RIM4PFRICSIV7KH6KNRMPO6X","short_pith_number":"pith:S4RIM4PF","canonical_record":{"source":{"id":"1212.1524","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2012-12-07T03:14:50Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"835fd09fb452893cda5c1dc94a6c265ebf94c55f34754bc50b9d1f276c7b2e5f","abstract_canon_sha256":"74d134247f05f2c576e57083828ccb04dc28c04454025ff7619f8b480cfb10df"},"schema_version":"1.0"},"canonical_sha256":"97228671e58a052457ea3f94d8b1eef5c26a3514a9730139c0e6c66efb0307c0","source":{"kind":"arxiv","id":"1212.1524","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1212.1524","created_at":"2026-05-18T03:33:25Z"},{"alias_kind":"arxiv_version","alias_value":"1212.1524v2","created_at":"2026-05-18T03:33:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1212.1524","created_at":"2026-05-18T03:33:25Z"},{"alias_kind":"pith_short_12","alias_value":"S4RIM4PFRICS","created_at":"2026-05-18T12:27:20Z"},{"alias_kind":"pith_short_16","alias_value":"S4RIM4PFRICSIV7K","created_at":"2026-05-18T12:27:20Z"},{"alias_kind":"pith_short_8","alias_value":"S4RIM4PF","created_at":"2026-05-18T12:27:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2012:S4RIM4PFRICSIV7KH6KNRMPO6X","target":"record","payload":{"canonical_record":{"source":{"id":"1212.1524","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2012-12-07T03:14:50Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"835fd09fb452893cda5c1dc94a6c265ebf94c55f34754bc50b9d1f276c7b2e5f","abstract_canon_sha256":"74d134247f05f2c576e57083828ccb04dc28c04454025ff7619f8b480cfb10df"},"schema_version":"1.0"},"canonical_sha256":"97228671e58a052457ea3f94d8b1eef5c26a3514a9730139c0e6c66efb0307c0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:33:25.342257Z","signature_b64":"bGwvFpPWFj1zI6YRQZHX+VzLbHWVvsv3Yrfq5bm9rGKwb6IWhFlFgayqIh5x1UutEIg3KGQd+vw0q1FbxPi1Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"97228671e58a052457ea3f94d8b1eef5c26a3514a9730139c0e6c66efb0307c0","last_reissued_at":"2026-05-18T03:33:25.341552Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:33:25.341552Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1212.1524","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":"2026-05-18T03:33:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gFByS5xZEXvBSiEFbBeMOBgVnQKkDHENZaNliMuk37bQVU0sjQ5EShUJb0qHhGDr2zjiK43QxTPNnRHdbSy2CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T02:31:11.806140Z"},"content_sha256":"223b61149a6b27c3a9175cae2a8fce6ad94a2d9bd1988c8bc22af276682a343d","schema_version":"1.0","event_id":"sha256:223b61149a6b27c3a9175cae2a8fce6ad94a2d9bd1988c8bc22af276682a343d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2012:S4RIM4PFRICSIV7KH6KNRMPO6X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Layer-wise learning of deep generative models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.NE","authors_text":"Ludovic Arnold, Yann Ollivier","submitted_at":"2012-12-07T03:14:50Z","abstract_excerpt":"When using deep, multi-layered architectures to build generative models of data, it is difficult to train all layers at once. We propose a layer-wise training procedure admitting a performance guarantee compared to the global optimum. It is based on an optimistic proxy of future performance, the best latent marginal. We interpret auto-encoders in this setting as generative models, by showing that they train a lower bound of this criterion. We test the new learning procedure against a state of the art method (stacked RBMs), and find it to improve performance. Both theory and experiments highlig"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1212.1524","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":"2026-05-18T03:33:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QyiIubS9ouRe3WN44LtEP9PXPHBy1wnqrHrFYNW1+3wzmaXwiOzbIhXduw1cQFpOlT2tNAk8HSk02Bu12oEtAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T02:31:11.806542Z"},"content_sha256":"fe172686515e52c71fca580b28c6d72a0375206bc005eae4be14e75e21be72ef","schema_version":"1.0","event_id":"sha256:fe172686515e52c71fca580b28c6d72a0375206bc005eae4be14e75e21be72ef"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/S4RIM4PFRICSIV7KH6KNRMPO6X/bundle.json","state_url":"https://pith.science/pith/S4RIM4PFRICSIV7KH6KNRMPO6X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/S4RIM4PFRICSIV7KH6KNRMPO6X/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":"2026-06-06T02:31:11Z","links":{"resolver":"https://pith.science/pith/S4RIM4PFRICSIV7KH6KNRMPO6X","bundle":"https://pith.science/pith/S4RIM4PFRICSIV7KH6KNRMPO6X/bundle.json","state":"https://pith.science/pith/S4RIM4PFRICSIV7KH6KNRMPO6X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/S4RIM4PFRICSIV7KH6KNRMPO6X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:S4RIM4PFRICSIV7KH6KNRMPO6X","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":"74d134247f05f2c576e57083828ccb04dc28c04454025ff7619f8b480cfb10df","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2012-12-07T03:14:50Z","title_canon_sha256":"835fd09fb452893cda5c1dc94a6c265ebf94c55f34754bc50b9d1f276c7b2e5f"},"schema_version":"1.0","source":{"id":"1212.1524","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1212.1524","created_at":"2026-05-18T03:33:25Z"},{"alias_kind":"arxiv_version","alias_value":"1212.1524v2","created_at":"2026-05-18T03:33:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1212.1524","created_at":"2026-05-18T03:33:25Z"},{"alias_kind":"pith_short_12","alias_value":"S4RIM4PFRICS","created_at":"2026-05-18T12:27:20Z"},{"alias_kind":"pith_short_16","alias_value":"S4RIM4PFRICSIV7K","created_at":"2026-05-18T12:27:20Z"},{"alias_kind":"pith_short_8","alias_value":"S4RIM4PF","created_at":"2026-05-18T12:27:20Z"}],"graph_snapshots":[{"event_id":"sha256:fe172686515e52c71fca580b28c6d72a0375206bc005eae4be14e75e21be72ef","target":"graph","created_at":"2026-05-18T03:33:25Z","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":"When using deep, multi-layered architectures to build generative models of data, it is difficult to train all layers at once. We propose a layer-wise training procedure admitting a performance guarantee compared to the global optimum. It is based on an optimistic proxy of future performance, the best latent marginal. We interpret auto-encoders in this setting as generative models, by showing that they train a lower bound of this criterion. We test the new learning procedure against a state of the art method (stacked RBMs), and find it to improve performance. Both theory and experiments highlig","authors_text":"Ludovic Arnold, Yann Ollivier","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2012-12-07T03:14:50Z","title":"Layer-wise learning of deep generative models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1212.1524","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":"sha256:223b61149a6b27c3a9175cae2a8fce6ad94a2d9bd1988c8bc22af276682a343d","target":"record","created_at":"2026-05-18T03:33:25Z","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":"74d134247f05f2c576e57083828ccb04dc28c04454025ff7619f8b480cfb10df","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2012-12-07T03:14:50Z","title_canon_sha256":"835fd09fb452893cda5c1dc94a6c265ebf94c55f34754bc50b9d1f276c7b2e5f"},"schema_version":"1.0","source":{"id":"1212.1524","kind":"arxiv","version":2}},"canonical_sha256":"97228671e58a052457ea3f94d8b1eef5c26a3514a9730139c0e6c66efb0307c0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"97228671e58a052457ea3f94d8b1eef5c26a3514a9730139c0e6c66efb0307c0","first_computed_at":"2026-05-18T03:33:25.341552Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:33:25.341552Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bGwvFpPWFj1zI6YRQZHX+VzLbHWVvsv3Yrfq5bm9rGKwb6IWhFlFgayqIh5x1UutEIg3KGQd+vw0q1FbxPi1Aw==","signature_status":"signed_v1","signed_at":"2026-05-18T03:33:25.342257Z","signed_message":"canonical_sha256_bytes"},"source_id":"1212.1524","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:223b61149a6b27c3a9175cae2a8fce6ad94a2d9bd1988c8bc22af276682a343d","sha256:fe172686515e52c71fca580b28c6d72a0375206bc005eae4be14e75e21be72ef"],"state_sha256":"4171238eff5ec3b992864ce64570255cf4642594067f7462c9453a0bccb721a2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DCAzKpCzOeCvJ1Cm9SggYLc/Rn7lrhNY50YiUOX/icrHLLyqbkPutcKRqAGpj/zpBRrI/2D1ARo0kYxTlGF7Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T02:31:11.808431Z","bundle_sha256":"7b725ee8d3b4e6768dc45b81b0592788251b37ba6bdf4204dcc4daaf20cf23ae"}}