{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:252L7IXVKV2FCSNHZXMCYT2QOA","short_pith_number":"pith:252L7IXV","canonical_record":{"source":{"id":"1811.03259","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-08T04:15:28Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"51fe147ebb1309862ce1614c03dd0a7b5251d2c40108dae33688323594164a18","abstract_canon_sha256":"5952d2995e4eedbfc086c6991f9ea9e658c5163bbc2ce6dfac373370f94c49af"},"schema_version":"1.0"},"canonical_sha256":"d774bfa2f555745149a7cdd82c4f5070361ff7cca4be01bf072e167e5af96795","source":{"kind":"arxiv","id":"1811.03259","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.03259","created_at":"2026-05-18T00:01:17Z"},{"alias_kind":"arxiv_version","alias_value":"1811.03259v1","created_at":"2026-05-18T00:01:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.03259","created_at":"2026-05-18T00:01:17Z"},{"alias_kind":"pith_short_12","alias_value":"252L7IXVKV2F","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_16","alias_value":"252L7IXVKV2FCSNH","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_8","alias_value":"252L7IXV","created_at":"2026-05-18T12:31:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:252L7IXVKV2FCSNHZXMCYT2QOA","target":"record","payload":{"canonical_record":{"source":{"id":"1811.03259","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-08T04:15:28Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"51fe147ebb1309862ce1614c03dd0a7b5251d2c40108dae33688323594164a18","abstract_canon_sha256":"5952d2995e4eedbfc086c6991f9ea9e658c5163bbc2ce6dfac373370f94c49af"},"schema_version":"1.0"},"canonical_sha256":"d774bfa2f555745149a7cdd82c4f5070361ff7cca4be01bf072e167e5af96795","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:17.133705Z","signature_b64":"RT0H2kKPVZ00ySpmLhvkfLbeSwPy4YjtmElTnerKnSHs3sRRBwRSy8kQq9RIQkVxN29ZQ9tKk8ZV65e7U/RyBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d774bfa2f555745149a7cdd82c4f5070361ff7cca4be01bf072e167e5af96795","last_reissued_at":"2026-05-18T00:01:17.133074Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:17.133074Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.03259","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":"2026-05-18T00:01:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lzK7KMqzReG/nFb9sid1G6LP+4lVxnZjfWCqmvweDo0bX0Om4flwSaPpRyBVr5vASsgwdS9+peqbz3pB0nw2Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T20:44:50.621776Z"},"content_sha256":"f405f26494f7e79a4e585eddbcfd2dcf3ce0b2c3fe9422719ee2807c358b1096","schema_version":"1.0","event_id":"sha256:f405f26494f7e79a4e585eddbcfd2dcf3ce0b2c3fe9422719ee2807c358b1096"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:252L7IXVKV2FCSNHZXMCYT2QOA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bias and Generalization in Deep Generative Models: An Empirical Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Arianna Yuan, Hongyu Ren, Jiaming Song, Noah Goodman, Shengjia Zhao, Stefano Ermon","submitted_at":"2018-11-08T04:15:28Z","abstract_excerpt":"In high dimensional settings, density estimation algorithms rely crucially on their inductive bias. Despite recent empirical success, the inductive bias of deep generative models is not well understood. In this paper we propose a framework to systematically investigate bias and generalization in deep generative models of images. Inspired by experimental methods from cognitive psychology, we probe each learning algorithm with carefully designed training datasets to characterize when and how existing models generate novel attributes and their combinations. We identify similarities to human psych"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.03259","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":"2026-05-18T00:01:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SeivO0pM3I8vBII8PaZLXE0rBr5LSHiqy7KxHIXUAY2jVn4sV8+sE6/kqF6Tm/NetXJRANZ1YpQdBZKOseDDBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T20:44:50.622459Z"},"content_sha256":"95a8395a44ae4918da0ee1853b1d85dec140249a245ec3da5bada51182858c6b","schema_version":"1.0","event_id":"sha256:95a8395a44ae4918da0ee1853b1d85dec140249a245ec3da5bada51182858c6b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/252L7IXVKV2FCSNHZXMCYT2QOA/bundle.json","state_url":"https://pith.science/pith/252L7IXVKV2FCSNHZXMCYT2QOA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/252L7IXVKV2FCSNHZXMCYT2QOA/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":"2026-05-27T20:44:50Z","links":{"resolver":"https://pith.science/pith/252L7IXVKV2FCSNHZXMCYT2QOA","bundle":"https://pith.science/pith/252L7IXVKV2FCSNHZXMCYT2QOA/bundle.json","state":"https://pith.science/pith/252L7IXVKV2FCSNHZXMCYT2QOA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/252L7IXVKV2FCSNHZXMCYT2QOA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:252L7IXVKV2FCSNHZXMCYT2QOA","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":"5952d2995e4eedbfc086c6991f9ea9e658c5163bbc2ce6dfac373370f94c49af","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-08T04:15:28Z","title_canon_sha256":"51fe147ebb1309862ce1614c03dd0a7b5251d2c40108dae33688323594164a18"},"schema_version":"1.0","source":{"id":"1811.03259","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.03259","created_at":"2026-05-18T00:01:17Z"},{"alias_kind":"arxiv_version","alias_value":"1811.03259v1","created_at":"2026-05-18T00:01:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.03259","created_at":"2026-05-18T00:01:17Z"},{"alias_kind":"pith_short_12","alias_value":"252L7IXVKV2F","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_16","alias_value":"252L7IXVKV2FCSNH","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_8","alias_value":"252L7IXV","created_at":"2026-05-18T12:31:59Z"}],"graph_snapshots":[{"event_id":"sha256:95a8395a44ae4918da0ee1853b1d85dec140249a245ec3da5bada51182858c6b","target":"graph","created_at":"2026-05-18T00:01:17Z","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":"In high dimensional settings, density estimation algorithms rely crucially on their inductive bias. Despite recent empirical success, the inductive bias of deep generative models is not well understood. In this paper we propose a framework to systematically investigate bias and generalization in deep generative models of images. Inspired by experimental methods from cognitive psychology, we probe each learning algorithm with carefully designed training datasets to characterize when and how existing models generate novel attributes and their combinations. We identify similarities to human psych","authors_text":"Arianna Yuan, Hongyu Ren, Jiaming Song, Noah Goodman, Shengjia Zhao, Stefano Ermon","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-08T04:15:28Z","title":"Bias and Generalization in Deep Generative Models: An Empirical Study"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.03259","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:f405f26494f7e79a4e585eddbcfd2dcf3ce0b2c3fe9422719ee2807c358b1096","target":"record","created_at":"2026-05-18T00:01:17Z","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":"5952d2995e4eedbfc086c6991f9ea9e658c5163bbc2ce6dfac373370f94c49af","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-08T04:15:28Z","title_canon_sha256":"51fe147ebb1309862ce1614c03dd0a7b5251d2c40108dae33688323594164a18"},"schema_version":"1.0","source":{"id":"1811.03259","kind":"arxiv","version":1}},"canonical_sha256":"d774bfa2f555745149a7cdd82c4f5070361ff7cca4be01bf072e167e5af96795","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d774bfa2f555745149a7cdd82c4f5070361ff7cca4be01bf072e167e5af96795","first_computed_at":"2026-05-18T00:01:17.133074Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:01:17.133074Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RT0H2kKPVZ00ySpmLhvkfLbeSwPy4YjtmElTnerKnSHs3sRRBwRSy8kQq9RIQkVxN29ZQ9tKk8ZV65e7U/RyBw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:01:17.133705Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.03259","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f405f26494f7e79a4e585eddbcfd2dcf3ce0b2c3fe9422719ee2807c358b1096","sha256:95a8395a44ae4918da0ee1853b1d85dec140249a245ec3da5bada51182858c6b"],"state_sha256":"91f918683f6a596da96e864f71574dca7029e4f98c534e12f27e40f405729f11"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z+G7B3cV9QtcT9M39L7cATIu+w5TvddyvSUZw8DMkrd3HaPrp138hQRBwxkx5ZePSNFXtPcgXinVA9UROi3nCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T20:44:50.625733Z","bundle_sha256":"9c20b02109efb7b646a5172aec9ab516dcadcad5cfff70d9edf589de44b68c0b"}}