{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:UPWNGY3IHNHS3SVTDKZNWYIEU7","short_pith_number":"pith:UPWNGY3I","canonical_record":{"source":{"id":"1902.00057","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-31T20:14:03Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ef37870127477942a9e02def98effa41f2685ee9887eed8ea9077b398e64fc2f","abstract_canon_sha256":"c85fa859edcbb70ca10ada7b6742c07adea74fb3fb79c792b3d1c6778652b41c"},"schema_version":"1.0"},"canonical_sha256":"a3ecd363683b4f2dcab31ab2db6104a7e192097cc3a1f0e804a9b5e789561c48","source":{"kind":"arxiv","id":"1902.00057","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.00057","created_at":"2026-05-17T23:54:58Z"},{"alias_kind":"arxiv_version","alias_value":"1902.00057v1","created_at":"2026-05-17T23:54:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.00057","created_at":"2026-05-17T23:54:58Z"},{"alias_kind":"pith_short_12","alias_value":"UPWNGY3IHNHS","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"UPWNGY3IHNHS3SVT","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"UPWNGY3I","created_at":"2026-05-18T12:33:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:UPWNGY3IHNHS3SVTDKZNWYIEU7","target":"record","payload":{"canonical_record":{"source":{"id":"1902.00057","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-31T20:14:03Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ef37870127477942a9e02def98effa41f2685ee9887eed8ea9077b398e64fc2f","abstract_canon_sha256":"c85fa859edcbb70ca10ada7b6742c07adea74fb3fb79c792b3d1c6778652b41c"},"schema_version":"1.0"},"canonical_sha256":"a3ecd363683b4f2dcab31ab2db6104a7e192097cc3a1f0e804a9b5e789561c48","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:58.344874Z","signature_b64":"GLl5JukC+EL/99MRxFzng4ND7whAj3PcyyaO4TofH/tMoYDd3LsmpeL3B45NmThjn/oQKSlLDuWHmjV8tG3pCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a3ecd363683b4f2dcab31ab2db6104a7e192097cc3a1f0e804a9b5e789561c48","last_reissued_at":"2026-05-17T23:54:58.344215Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:58.344215Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1902.00057","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":"2026-05-17T23:54:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Yx7mnZtYo24sM0r7uyf49sxjps2/UZDkHFfvZd3QolESsFlLXUSHcyGP40gp6qO5FkukkqKR+d5WGlY0t/7hAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T04:22:35.562949Z"},"content_sha256":"53e9e901eb075e9d161f6b7da704ff84d1f96a9a465dc1785d934dd1035f2754","schema_version":"1.0","event_id":"sha256:53e9e901eb075e9d161f6b7da704ff84d1f96a9a465dc1785d934dd1035f2754"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:UPWNGY3IHNHS3SVTDKZNWYIEU7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Probabilistic Discriminative Learning with Layered Graphical Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Csaba Domokos, Daniel Cremers, Tao Wu, Yuesong Shen","submitted_at":"2019-01-31T20:14:03Z","abstract_excerpt":"Probabilistic graphical models are traditionally known for their successes in generative modeling. In this work, we advocate layered graphical models (LGMs) for probabilistic discriminative learning. To this end, we design LGMs in close analogy to neural networks (NNs), that is, they have deep hierarchical structures and convolutional or local connections between layers. Equipped with tensorized truncated variational inference, our LGMs can be efficiently trained via backpropagation on mainstream deep learning frameworks such as PyTorch. To deal with continuous valued inputs, we use a simple y"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.00057","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":"2026-05-17T23:54:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3fqu+N6M8InXwbtR2uefmA1KpCvOOADLiTWVdLNGLbh7/31nXffy1XwvGQ+SFy2QZ7pDM5zocD39eZVbV52xBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T04:22:35.563682Z"},"content_sha256":"407012f9200570121818de0e566db0c4b3fb84db9f04c5bfcad2515f05393b7a","schema_version":"1.0","event_id":"sha256:407012f9200570121818de0e566db0c4b3fb84db9f04c5bfcad2515f05393b7a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UPWNGY3IHNHS3SVTDKZNWYIEU7/bundle.json","state_url":"https://pith.science/pith/UPWNGY3IHNHS3SVTDKZNWYIEU7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UPWNGY3IHNHS3SVTDKZNWYIEU7/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":"2026-06-06T04:22:35Z","links":{"resolver":"https://pith.science/pith/UPWNGY3IHNHS3SVTDKZNWYIEU7","bundle":"https://pith.science/pith/UPWNGY3IHNHS3SVTDKZNWYIEU7/bundle.json","state":"https://pith.science/pith/UPWNGY3IHNHS3SVTDKZNWYIEU7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UPWNGY3IHNHS3SVTDKZNWYIEU7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:UPWNGY3IHNHS3SVTDKZNWYIEU7","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":"c85fa859edcbb70ca10ada7b6742c07adea74fb3fb79c792b3d1c6778652b41c","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-31T20:14:03Z","title_canon_sha256":"ef37870127477942a9e02def98effa41f2685ee9887eed8ea9077b398e64fc2f"},"schema_version":"1.0","source":{"id":"1902.00057","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.00057","created_at":"2026-05-17T23:54:58Z"},{"alias_kind":"arxiv_version","alias_value":"1902.00057v1","created_at":"2026-05-17T23:54:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.00057","created_at":"2026-05-17T23:54:58Z"},{"alias_kind":"pith_short_12","alias_value":"UPWNGY3IHNHS","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"UPWNGY3IHNHS3SVT","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"UPWNGY3I","created_at":"2026-05-18T12:33:30Z"}],"graph_snapshots":[{"event_id":"sha256:407012f9200570121818de0e566db0c4b3fb84db9f04c5bfcad2515f05393b7a","target":"graph","created_at":"2026-05-17T23:54:58Z","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":"Probabilistic graphical models are traditionally known for their successes in generative modeling. In this work, we advocate layered graphical models (LGMs) for probabilistic discriminative learning. To this end, we design LGMs in close analogy to neural networks (NNs), that is, they have deep hierarchical structures and convolutional or local connections between layers. Equipped with tensorized truncated variational inference, our LGMs can be efficiently trained via backpropagation on mainstream deep learning frameworks such as PyTorch. To deal with continuous valued inputs, we use a simple y","authors_text":"Csaba Domokos, Daniel Cremers, Tao Wu, Yuesong Shen","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-31T20:14:03Z","title":"Probabilistic Discriminative Learning with Layered Graphical Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.00057","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":"sha256:53e9e901eb075e9d161f6b7da704ff84d1f96a9a465dc1785d934dd1035f2754","target":"record","created_at":"2026-05-17T23:54:58Z","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":"c85fa859edcbb70ca10ada7b6742c07adea74fb3fb79c792b3d1c6778652b41c","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-31T20:14:03Z","title_canon_sha256":"ef37870127477942a9e02def98effa41f2685ee9887eed8ea9077b398e64fc2f"},"schema_version":"1.0","source":{"id":"1902.00057","kind":"arxiv","version":1}},"canonical_sha256":"a3ecd363683b4f2dcab31ab2db6104a7e192097cc3a1f0e804a9b5e789561c48","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a3ecd363683b4f2dcab31ab2db6104a7e192097cc3a1f0e804a9b5e789561c48","first_computed_at":"2026-05-17T23:54:58.344215Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:54:58.344215Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GLl5JukC+EL/99MRxFzng4ND7whAj3PcyyaO4TofH/tMoYDd3LsmpeL3B45NmThjn/oQKSlLDuWHmjV8tG3pCg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:54:58.344874Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.00057","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:53e9e901eb075e9d161f6b7da704ff84d1f96a9a465dc1785d934dd1035f2754","sha256:407012f9200570121818de0e566db0c4b3fb84db9f04c5bfcad2515f05393b7a"],"state_sha256":"c9a4589314e7a0fba2665988a6fa0a17badc6a2708050c89fb0dae3f3ad4216b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/vieUWTOOAG3j6SiMFH68rb08N3lZDx59bvo4K9M4sCoQwLCiU5AtLooe/CMASb7K9v8QIdOStfJshdADF8vBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T04:22:35.567413Z","bundle_sha256":"16fd9924d09e1f03f262d03d8cc8d945957480dc4f3fd28e4fdef168d96caeb2"}}