{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:PLLPJ5DU3DEGDNNLTOJJWWX6FM","short_pith_number":"pith:PLLPJ5DU","canonical_record":{"source":{"id":"1506.04720","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-06-15T19:34:59Z","cross_cats_sorted":[],"title_canon_sha256":"683b256f6fa9f89b91329616121eefa0d8900920752885a5627b87714711904c","abstract_canon_sha256":"03037b38733e88971cef6da5538a273f4f250adc2abb0e4b179c3b81aea1effc"},"schema_version":"1.0"},"canonical_sha256":"7ad6f4f474d8c861b5ab9b929b5afe2b28ab741c277b36823e6c1c2a365d4828","source":{"kind":"arxiv","id":"1506.04720","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1506.04720","created_at":"2026-05-18T01:49:25Z"},{"alias_kind":"arxiv_version","alias_value":"1506.04720v1","created_at":"2026-05-18T01:49:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.04720","created_at":"2026-05-18T01:49:25Z"},{"alias_kind":"pith_short_12","alias_value":"PLLPJ5DU3DEG","created_at":"2026-05-18T12:29:37Z"},{"alias_kind":"pith_short_16","alias_value":"PLLPJ5DU3DEGDNNL","created_at":"2026-05-18T12:29:37Z"},{"alias_kind":"pith_short_8","alias_value":"PLLPJ5DU","created_at":"2026-05-18T12:29:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:PLLPJ5DU3DEGDNNLTOJJWWX6FM","target":"record","payload":{"canonical_record":{"source":{"id":"1506.04720","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-06-15T19:34:59Z","cross_cats_sorted":[],"title_canon_sha256":"683b256f6fa9f89b91329616121eefa0d8900920752885a5627b87714711904c","abstract_canon_sha256":"03037b38733e88971cef6da5538a273f4f250adc2abb0e4b179c3b81aea1effc"},"schema_version":"1.0"},"canonical_sha256":"7ad6f4f474d8c861b5ab9b929b5afe2b28ab741c277b36823e6c1c2a365d4828","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:49:25.092277Z","signature_b64":"nXDrikCflcnNeE461VILZftTuk3ShP3TUrRxnxFS/27A0O/EKPUVe1A2hQKhE0k58sKDhzpqXGOJBfxT0QMECg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ad6f4f474d8c861b5ab9b929b5afe2b28ab741c277b36823e6c1c2a365d4828","last_reissued_at":"2026-05-18T01:49:25.091624Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:49:25.091624Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1506.04720","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":"2026-05-18T01:49:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z05jdxWDZ3obu7BDtqb3ExV9sd9DrxNfO/keBOpaJAVUxkh8nKWXn+aSe3rbcIS1taRcfp5XQiROJLLnelSXCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T13:36:48.677129Z"},"content_sha256":"d76484c212c00e81b428b49aeea0bcb097d3d7cdb9524b9faec2329bd5ece84a","schema_version":"1.0","event_id":"sha256:d76484c212c00e81b428b49aeea0bcb097d3d7cdb9524b9faec2329bd5ece84a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:PLLPJ5DU3DEGDNNLTOJJWWX6FM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Latent Regression Bayesian Network for Data Representation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Qiang Ji, Siqi Nie","submitted_at":"2015-06-15T19:34:59Z","abstract_excerpt":"Deep directed generative models have attracted much attention recently due to their expressive representation power and the ability of ancestral sampling. One major difficulty of learning directed models with many latent variables is the intractable inference. To address this problem, most existing algorithms make assumptions to render the latent variables independent of each other, either by designing specific priors, or by approximating the true posterior using a factorized distribution. We believe the correlations among latent variables are crucial for faithful data representation. Driven b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.04720","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":"2026-05-18T01:49:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"olDTllTOplkLs+ff+L0l4hKCpqZJbPbz5sfu74sAPQuKnvuoCn6qTGUOEr6Iv/EJq6zIoCrCbnCxiBhZFPClDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T13:36:48.677496Z"},"content_sha256":"ae0b1b0c2f4eac8ddec0f45ddfdeb4c1e68f2832b35f00a6096f655f0012dc1d","schema_version":"1.0","event_id":"sha256:ae0b1b0c2f4eac8ddec0f45ddfdeb4c1e68f2832b35f00a6096f655f0012dc1d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PLLPJ5DU3DEGDNNLTOJJWWX6FM/bundle.json","state_url":"https://pith.science/pith/PLLPJ5DU3DEGDNNLTOJJWWX6FM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PLLPJ5DU3DEGDNNLTOJJWWX6FM/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":"2026-05-28T13:36:48Z","links":{"resolver":"https://pith.science/pith/PLLPJ5DU3DEGDNNLTOJJWWX6FM","bundle":"https://pith.science/pith/PLLPJ5DU3DEGDNNLTOJJWWX6FM/bundle.json","state":"https://pith.science/pith/PLLPJ5DU3DEGDNNLTOJJWWX6FM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PLLPJ5DU3DEGDNNLTOJJWWX6FM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:PLLPJ5DU3DEGDNNLTOJJWWX6FM","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":"03037b38733e88971cef6da5538a273f4f250adc2abb0e4b179c3b81aea1effc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-06-15T19:34:59Z","title_canon_sha256":"683b256f6fa9f89b91329616121eefa0d8900920752885a5627b87714711904c"},"schema_version":"1.0","source":{"id":"1506.04720","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1506.04720","created_at":"2026-05-18T01:49:25Z"},{"alias_kind":"arxiv_version","alias_value":"1506.04720v1","created_at":"2026-05-18T01:49:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.04720","created_at":"2026-05-18T01:49:25Z"},{"alias_kind":"pith_short_12","alias_value":"PLLPJ5DU3DEG","created_at":"2026-05-18T12:29:37Z"},{"alias_kind":"pith_short_16","alias_value":"PLLPJ5DU3DEGDNNL","created_at":"2026-05-18T12:29:37Z"},{"alias_kind":"pith_short_8","alias_value":"PLLPJ5DU","created_at":"2026-05-18T12:29:37Z"}],"graph_snapshots":[{"event_id":"sha256:ae0b1b0c2f4eac8ddec0f45ddfdeb4c1e68f2832b35f00a6096f655f0012dc1d","target":"graph","created_at":"2026-05-18T01:49:25Z","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":"Deep directed generative models have attracted much attention recently due to their expressive representation power and the ability of ancestral sampling. One major difficulty of learning directed models with many latent variables is the intractable inference. To address this problem, most existing algorithms make assumptions to render the latent variables independent of each other, either by designing specific priors, or by approximating the true posterior using a factorized distribution. We believe the correlations among latent variables are crucial for faithful data representation. Driven b","authors_text":"Qiang Ji, Siqi Nie","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-06-15T19:34:59Z","title":"Latent Regression Bayesian Network for Data Representation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.04720","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:d76484c212c00e81b428b49aeea0bcb097d3d7cdb9524b9faec2329bd5ece84a","target":"record","created_at":"2026-05-18T01:49:25Z","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":"03037b38733e88971cef6da5538a273f4f250adc2abb0e4b179c3b81aea1effc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-06-15T19:34:59Z","title_canon_sha256":"683b256f6fa9f89b91329616121eefa0d8900920752885a5627b87714711904c"},"schema_version":"1.0","source":{"id":"1506.04720","kind":"arxiv","version":1}},"canonical_sha256":"7ad6f4f474d8c861b5ab9b929b5afe2b28ab741c277b36823e6c1c2a365d4828","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7ad6f4f474d8c861b5ab9b929b5afe2b28ab741c277b36823e6c1c2a365d4828","first_computed_at":"2026-05-18T01:49:25.091624Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:49:25.091624Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nXDrikCflcnNeE461VILZftTuk3ShP3TUrRxnxFS/27A0O/EKPUVe1A2hQKhE0k58sKDhzpqXGOJBfxT0QMECg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:49:25.092277Z","signed_message":"canonical_sha256_bytes"},"source_id":"1506.04720","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d76484c212c00e81b428b49aeea0bcb097d3d7cdb9524b9faec2329bd5ece84a","sha256:ae0b1b0c2f4eac8ddec0f45ddfdeb4c1e68f2832b35f00a6096f655f0012dc1d"],"state_sha256":"51bc5b26edaefe331825b17b1284eebab80712c8478196699bcf3d80f2891102"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"02WgPrBDJJBjXbYIGX3XpoYnCsCG5PmU8pipUQPYi029iYQzY9EP41UC80gLgJwbM3PRIQH74KzDw1wTaFa9AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T13:36:48.680475Z","bundle_sha256":"8e6c7d01eddb1078806f7381257d07ddbced6d35b6cd13f8fefb40354912d8c3"}}