{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:ZI2EJZMWMNS7NUSRQ6EDB7QIFP","short_pith_number":"pith:ZI2EJZMW","canonical_record":{"source":{"id":"1905.10887","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-26T21:41:44Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1ea3757376821040beae3fc65df447664975b5b5e4070d3f6a916d5deca2985f","abstract_canon_sha256":"7207e7fe52cc5c8bb8c6ddd97d91182076076c16d735ed7e63a4e1448dfc35aa"},"schema_version":"1.0"},"canonical_sha256":"ca3444e5966365f6d251878830fe082bd0510dde823f0bb2680c351565ae57fc","source":{"kind":"arxiv","id":"1905.10887","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.10887","created_at":"2026-07-05T00:15:05Z"},{"alias_kind":"arxiv_version","alias_value":"1905.10887v2","created_at":"2026-07-05T00:15:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.10887","created_at":"2026-07-05T00:15:05Z"},{"alias_kind":"pith_short_12","alias_value":"ZI2EJZMWMNS7","created_at":"2026-07-05T00:15:05Z"},{"alias_kind":"pith_short_16","alias_value":"ZI2EJZMWMNS7NUSR","created_at":"2026-07-05T00:15:05Z"},{"alias_kind":"pith_short_8","alias_value":"ZI2EJZMW","created_at":"2026-07-05T00:15:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:ZI2EJZMWMNS7NUSRQ6EDB7QIFP","target":"record","payload":{"canonical_record":{"source":{"id":"1905.10887","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-26T21:41:44Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1ea3757376821040beae3fc65df447664975b5b5e4070d3f6a916d5deca2985f","abstract_canon_sha256":"7207e7fe52cc5c8bb8c6ddd97d91182076076c16d735ed7e63a4e1448dfc35aa"},"schema_version":"1.0"},"canonical_sha256":"ca3444e5966365f6d251878830fe082bd0510dde823f0bb2680c351565ae57fc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:15:05.075012Z","signature_b64":"QBs2q0maoQNzAuuE4Z5GdLGyKzV0+f/5wdu297BmgsQPmyS5RKQZLXFVEDbezZHgKAIPMHLH5suQ297xtFf+DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca3444e5966365f6d251878830fe082bd0510dde823f0bb2680c351565ae57fc","last_reissued_at":"2026-07-05T00:15:05.074553Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:15:05.074553Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.10887","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":"2026-07-05T00:15:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MgrSK9WwZrSpeJba4Z3AwQsvovjbTJH5Aa1cuv/WmrzfPS0bYR62tKeUv1C66Gob2m9BvwY/tzHMIdUW7tGvAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T20:20:11.328817Z"},"content_sha256":"a0597c472b33050522eeb57890486c9798502e2aaf18038bfb9d4111c141cc7d","schema_version":"1.0","event_id":"sha256:a0597c472b33050522eeb57890486c9798502e2aaf18038bfb9d4111c141cc7d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:ZI2EJZMWMNS7NUSRQ6EDB7QIFP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Classification Accuracy Score for Conditional Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Oriol Vinyals, Suman Ravuri","submitted_at":"2019-05-26T21:41:44Z","abstract_excerpt":"Deep generative models (DGMs) of images are now sufficiently mature that they produce nearly photorealistic samples and obtain scores similar to the data distribution on heuristics such as Frechet Inception Distance (FID). These results, especially on large-scale datasets such as ImageNet, suggest that DGMs are learning the data distribution in a perceptually meaningful space and can be used in downstream tasks. To test this latter hypothesis, we use class-conditional generative models from a number of model classes---variational autoencoders, autoregressive models, and generative adversarial "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.10887","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1905.10887/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T00:15:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j8Lrbj1Rvq/KBtgeBhY4oNeaog/pwY5HWA5MgVoX9ce7AvIwkgohmLsOJ64b1x20GDw3T57PauT/5+csll3QCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T20:20:11.329613Z"},"content_sha256":"acb34aa84539f9d230450cfdeb7f9c087e16a723dbb27e718e95582dbf00bfeb","schema_version":"1.0","event_id":"sha256:acb34aa84539f9d230450cfdeb7f9c087e16a723dbb27e718e95582dbf00bfeb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZI2EJZMWMNS7NUSRQ6EDB7QIFP/bundle.json","state_url":"https://pith.science/pith/ZI2EJZMWMNS7NUSRQ6EDB7QIFP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZI2EJZMWMNS7NUSRQ6EDB7QIFP/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":"2026-08-03T20:20:11Z","links":{"resolver":"https://pith.science/pith/ZI2EJZMWMNS7NUSRQ6EDB7QIFP","bundle":"https://pith.science/pith/ZI2EJZMWMNS7NUSRQ6EDB7QIFP/bundle.json","state":"https://pith.science/pith/ZI2EJZMWMNS7NUSRQ6EDB7QIFP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZI2EJZMWMNS7NUSRQ6EDB7QIFP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:ZI2EJZMWMNS7NUSRQ6EDB7QIFP","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":"7207e7fe52cc5c8bb8c6ddd97d91182076076c16d735ed7e63a4e1448dfc35aa","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-26T21:41:44Z","title_canon_sha256":"1ea3757376821040beae3fc65df447664975b5b5e4070d3f6a916d5deca2985f"},"schema_version":"1.0","source":{"id":"1905.10887","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.10887","created_at":"2026-07-05T00:15:05Z"},{"alias_kind":"arxiv_version","alias_value":"1905.10887v2","created_at":"2026-07-05T00:15:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.10887","created_at":"2026-07-05T00:15:05Z"},{"alias_kind":"pith_short_12","alias_value":"ZI2EJZMWMNS7","created_at":"2026-07-05T00:15:05Z"},{"alias_kind":"pith_short_16","alias_value":"ZI2EJZMWMNS7NUSR","created_at":"2026-07-05T00:15:05Z"},{"alias_kind":"pith_short_8","alias_value":"ZI2EJZMW","created_at":"2026-07-05T00:15:05Z"}],"graph_snapshots":[{"event_id":"sha256:acb34aa84539f9d230450cfdeb7f9c087e16a723dbb27e718e95582dbf00bfeb","target":"graph","created_at":"2026-07-05T00:15:05Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1905.10887/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep generative models (DGMs) of images are now sufficiently mature that they produce nearly photorealistic samples and obtain scores similar to the data distribution on heuristics such as Frechet Inception Distance (FID). These results, especially on large-scale datasets such as ImageNet, suggest that DGMs are learning the data distribution in a perceptually meaningful space and can be used in downstream tasks. To test this latter hypothesis, we use class-conditional generative models from a number of model classes---variational autoencoders, autoregressive models, and generative adversarial ","authors_text":"Oriol Vinyals, Suman Ravuri","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-26T21:41:44Z","title":"Classification Accuracy Score for Conditional Generative Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.10887","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:a0597c472b33050522eeb57890486c9798502e2aaf18038bfb9d4111c141cc7d","target":"record","created_at":"2026-07-05T00:15:05Z","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":"7207e7fe52cc5c8bb8c6ddd97d91182076076c16d735ed7e63a4e1448dfc35aa","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-26T21:41:44Z","title_canon_sha256":"1ea3757376821040beae3fc65df447664975b5b5e4070d3f6a916d5deca2985f"},"schema_version":"1.0","source":{"id":"1905.10887","kind":"arxiv","version":2}},"canonical_sha256":"ca3444e5966365f6d251878830fe082bd0510dde823f0bb2680c351565ae57fc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ca3444e5966365f6d251878830fe082bd0510dde823f0bb2680c351565ae57fc","first_computed_at":"2026-07-05T00:15:05.074553Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:15:05.074553Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QBs2q0maoQNzAuuE4Z5GdLGyKzV0+f/5wdu297BmgsQPmyS5RKQZLXFVEDbezZHgKAIPMHLH5suQ297xtFf+DA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:15:05.075012Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.10887","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a0597c472b33050522eeb57890486c9798502e2aaf18038bfb9d4111c141cc7d","sha256:acb34aa84539f9d230450cfdeb7f9c087e16a723dbb27e718e95582dbf00bfeb"],"state_sha256":"7cab323f3f3fd1bd7e47a1cc39e7a371196d5fdd430527b0d8192f48c922beef"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pacidRwLrwzQmlhCkTm7wQHfwzSZ1sN+V8ix01v2Ovcci9fLm4A/6raHnfA3bvaESn5guABnQErnEcPgtl7UAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T20:20:11.333938Z","bundle_sha256":"27389218e05e1762526010ab46fcac915d8b0b0d406b83d8b07676b4ac4c9593"}}