{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:XBKVXAFPU353UZQ6LJWVBISH6J","short_pith_number":"pith:XBKVXAFP","canonical_record":{"source":{"id":"1806.09764","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-26T02:31:35Z","cross_cats_sorted":["cs.CL","cs.CV","stat.ML"],"title_canon_sha256":"1b2f967b45f18b7a247583e2aafa566d576cfa5247ced77865cfee19ee5aa26d","abstract_canon_sha256":"157dbdb74b0254118e35909955f5eba6ee038684f1e8395c7caa55d074e46b7e"},"schema_version":"1.0"},"canonical_sha256":"b8555b80afa6fbba661e5a6d50a247f24d38876e7c588709c8f9ce504fa8a1d7","source":{"kind":"arxiv","id":"1806.09764","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.09764","created_at":"2026-05-18T00:00:19Z"},{"alias_kind":"arxiv_version","alias_value":"1806.09764v2","created_at":"2026-05-18T00:00:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.09764","created_at":"2026-05-18T00:00:19Z"},{"alias_kind":"pith_short_12","alias_value":"XBKVXAFPU353","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"XBKVXAFPU353UZQ6","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"XBKVXAFP","created_at":"2026-05-18T12:33:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:XBKVXAFPU353UZQ6LJWVBISH6J","target":"record","payload":{"canonical_record":{"source":{"id":"1806.09764","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-26T02:31:35Z","cross_cats_sorted":["cs.CL","cs.CV","stat.ML"],"title_canon_sha256":"1b2f967b45f18b7a247583e2aafa566d576cfa5247ced77865cfee19ee5aa26d","abstract_canon_sha256":"157dbdb74b0254118e35909955f5eba6ee038684f1e8395c7caa55d074e46b7e"},"schema_version":"1.0"},"canonical_sha256":"b8555b80afa6fbba661e5a6d50a247f24d38876e7c588709c8f9ce504fa8a1d7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:00:19.092025Z","signature_b64":"xehQFKQJR8FwFOt3PBuuebLp2Q7vMPYZK6VmWAIJDH08kfJRwy5KVwiin1IN5Xa0DQyJ/uecVuA4SVZCmLexCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b8555b80afa6fbba661e5a6d50a247f24d38876e7c588709c8f9ce504fa8a1d7","last_reissued_at":"2026-05-18T00:00:19.091435Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:00:19.091435Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1806.09764","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":"2026-05-18T00:00:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ambt5J5NXEl0zGglWLDwF0yCg6Vw0QTEglW/Adqw2zjmal5Kz9W2xUNDs7ge4Wan9XstNcowqKt0tBwTPrglDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T03:59:50.065000Z"},"content_sha256":"a3f8fa0765f2d24c3168b78707d675304e01f0287e6a58217ffecbaf8bce96c6","schema_version":"1.0","event_id":"sha256:a3f8fa0765f2d24c3168b78707d675304e01f0287e6a58217ffecbaf8bce96c6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:XBKVXAFPU353UZQ6LJWVBISH6J","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Generative Models with Learnable Knowledge Constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Eric Xing, Haoye Dong, Lianhui Qin, Ruslan Salakhutdinov, Xiaodan Liang, Zhiting Hu, Zichao Yang","submitted_at":"2018-06-26T02:31:35Z","abstract_excerpt":"The broad set of deep generative models (DGMs) has achieved remarkable advances. However, it is often difficult to incorporate rich structured domain knowledge with the end-to-end DGMs. Posterior regularization (PR) offers a principled framework to impose structured constraints on probabilistic models, but has limited applicability to the diverse DGMs that can lack a Bayesian formulation or even explicit density evaluation. PR also requires constraints to be fully specified a priori, which is impractical or suboptimal for complex knowledge with learnable uncertain parts. In this paper, we esta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.09764","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":"2026-05-18T00:00:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jb//DvIxQRzWe6qwvLKS0/016S/EJCU3J6AMVmPU89qOQLkBGkMq745spaer0CWlWHhE9u+Brgk1rFbAdYEIAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T03:59:50.065415Z"},"content_sha256":"dceaca03f2392cee34ded1faebc8dd2233e38465d4181d7491c3629f68f332ca","schema_version":"1.0","event_id":"sha256:dceaca03f2392cee34ded1faebc8dd2233e38465d4181d7491c3629f68f332ca"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XBKVXAFPU353UZQ6LJWVBISH6J/bundle.json","state_url":"https://pith.science/pith/XBKVXAFPU353UZQ6LJWVBISH6J/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XBKVXAFPU353UZQ6LJWVBISH6J/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":"2026-05-30T03:59:50Z","links":{"resolver":"https://pith.science/pith/XBKVXAFPU353UZQ6LJWVBISH6J","bundle":"https://pith.science/pith/XBKVXAFPU353UZQ6LJWVBISH6J/bundle.json","state":"https://pith.science/pith/XBKVXAFPU353UZQ6LJWVBISH6J/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XBKVXAFPU353UZQ6LJWVBISH6J/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:XBKVXAFPU353UZQ6LJWVBISH6J","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":"157dbdb74b0254118e35909955f5eba6ee038684f1e8395c7caa55d074e46b7e","cross_cats_sorted":["cs.CL","cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-26T02:31:35Z","title_canon_sha256":"1b2f967b45f18b7a247583e2aafa566d576cfa5247ced77865cfee19ee5aa26d"},"schema_version":"1.0","source":{"id":"1806.09764","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.09764","created_at":"2026-05-18T00:00:19Z"},{"alias_kind":"arxiv_version","alias_value":"1806.09764v2","created_at":"2026-05-18T00:00:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.09764","created_at":"2026-05-18T00:00:19Z"},{"alias_kind":"pith_short_12","alias_value":"XBKVXAFPU353","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"XBKVXAFPU353UZQ6","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"XBKVXAFP","created_at":"2026-05-18T12:33:01Z"}],"graph_snapshots":[{"event_id":"sha256:dceaca03f2392cee34ded1faebc8dd2233e38465d4181d7491c3629f68f332ca","target":"graph","created_at":"2026-05-18T00:00:19Z","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":"The broad set of deep generative models (DGMs) has achieved remarkable advances. However, it is often difficult to incorporate rich structured domain knowledge with the end-to-end DGMs. Posterior regularization (PR) offers a principled framework to impose structured constraints on probabilistic models, but has limited applicability to the diverse DGMs that can lack a Bayesian formulation or even explicit density evaluation. PR also requires constraints to be fully specified a priori, which is impractical or suboptimal for complex knowledge with learnable uncertain parts. In this paper, we esta","authors_text":"Eric Xing, Haoye Dong, Lianhui Qin, Ruslan Salakhutdinov, Xiaodan Liang, Zhiting Hu, Zichao Yang","cross_cats":["cs.CL","cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-26T02:31:35Z","title":"Deep Generative Models with Learnable Knowledge Constraints"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.09764","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:a3f8fa0765f2d24c3168b78707d675304e01f0287e6a58217ffecbaf8bce96c6","target":"record","created_at":"2026-05-18T00:00:19Z","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":"157dbdb74b0254118e35909955f5eba6ee038684f1e8395c7caa55d074e46b7e","cross_cats_sorted":["cs.CL","cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-26T02:31:35Z","title_canon_sha256":"1b2f967b45f18b7a247583e2aafa566d576cfa5247ced77865cfee19ee5aa26d"},"schema_version":"1.0","source":{"id":"1806.09764","kind":"arxiv","version":2}},"canonical_sha256":"b8555b80afa6fbba661e5a6d50a247f24d38876e7c588709c8f9ce504fa8a1d7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b8555b80afa6fbba661e5a6d50a247f24d38876e7c588709c8f9ce504fa8a1d7","first_computed_at":"2026-05-18T00:00:19.091435Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:00:19.091435Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xehQFKQJR8FwFOt3PBuuebLp2Q7vMPYZK6VmWAIJDH08kfJRwy5KVwiin1IN5Xa0DQyJ/uecVuA4SVZCmLexCw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:00:19.092025Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.09764","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a3f8fa0765f2d24c3168b78707d675304e01f0287e6a58217ffecbaf8bce96c6","sha256:dceaca03f2392cee34ded1faebc8dd2233e38465d4181d7491c3629f68f332ca"],"state_sha256":"b6606393e5910e0e68c1a1c5ed81f6ecb5f681b170e6cb5b98b9f77b3b143be9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2+jMnDZkFmuLp5fOLJSQ5nik4ElIWJB7XIRAyOxP8QmedOT+YTumZiMdfGTNFVbXNgGb+zwhN9zWJqJ2njwVAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T03:59:50.067469Z","bundle_sha256":"f53161fe7cc887ad41b8727e66bf2d2fe0c6bc1356a82820f16f297811904c15"}}