{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:ZJWEOS4KOQBY34GROIURDHFPHR","short_pith_number":"pith:ZJWEOS4K","canonical_record":{"source":{"id":"2105.13290","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-05-26T16:52:53Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f3da52acf16e06ca3f4a328144e9b4eae244cc5d4004cc76eb08bb4efe3f8962","abstract_canon_sha256":"ddb4aec60a1f95e4c42d0deba8ed79cc1124206a16e0fe87749942d575401e34"},"schema_version":"1.0"},"canonical_sha256":"ca6c474b8a74038df0d17229119caf3c73aa78b2c6871819407ad0b286a1f4b8","source":{"kind":"arxiv","id":"2105.13290","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.13290","created_at":"2026-07-05T03:29:16Z"},{"alias_kind":"arxiv_version","alias_value":"2105.13290v3","created_at":"2026-07-05T03:29:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.13290","created_at":"2026-07-05T03:29:16Z"},{"alias_kind":"pith_short_12","alias_value":"ZJWEOS4KOQBY","created_at":"2026-07-05T03:29:16Z"},{"alias_kind":"pith_short_16","alias_value":"ZJWEOS4KOQBY34GR","created_at":"2026-07-05T03:29:16Z"},{"alias_kind":"pith_short_8","alias_value":"ZJWEOS4K","created_at":"2026-07-05T03:29:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:ZJWEOS4KOQBY34GROIURDHFPHR","target":"record","payload":{"canonical_record":{"source":{"id":"2105.13290","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-05-26T16:52:53Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f3da52acf16e06ca3f4a328144e9b4eae244cc5d4004cc76eb08bb4efe3f8962","abstract_canon_sha256":"ddb4aec60a1f95e4c42d0deba8ed79cc1124206a16e0fe87749942d575401e34"},"schema_version":"1.0"},"canonical_sha256":"ca6c474b8a74038df0d17229119caf3c73aa78b2c6871819407ad0b286a1f4b8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:29:16.626812Z","signature_b64":"eBfqu/FtewsN2jm1/aZTjQmIqvnyjEsEPD4twEOG+xDR4nALbdonFhNWSWrtlenqrOnkYiGl+55wnwJLZ2j1Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca6c474b8a74038df0d17229119caf3c73aa78b2c6871819407ad0b286a1f4b8","last_reissued_at":"2026-07-05T03:29:16.626252Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:29:16.626252Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2105.13290","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:29:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N4DMRJSzgFQwck25wCJhXNPiJLzilqeuzkwZuYqIu2YThYt0fm78JKfyqaldDYkEXLng7EDEvdV1HbatkYNpAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T17:10:09.877813Z"},"content_sha256":"3829002c28a2b99e82f1c865718ff50323225e931b5a82180d8445bfbc020999","schema_version":"1.0","event_id":"sha256:3829002c28a2b99e82f1c865718ff50323225e931b5a82180d8445bfbc020999"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:ZJWEOS4KOQBY34GROIURDHFPHR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CogView: Mastering Text-to-Image Generation via Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Chang Zhou, Da Yin, Hongxia Yang, Jie Tang, Junyang Lin, Ming Ding, Wendi Zheng, Wenyi Hong, Xu Zou, Zhou Shao, Zhuoyi Yang","submitted_at":"2021-05-26T16:52:53Z","abstract_excerpt":"Text-to-Image generation in the general domain has long been an open problem, which requires both a powerful generative model and cross-modal understanding. We propose CogView, a 4-billion-parameter Transformer with VQ-VAE tokenizer to advance this problem. We also demonstrate the finetuning strategies for various downstream tasks, e.g. style learning, super-resolution, text-image ranking and fashion design, and methods to stabilize pretraining, e.g. eliminating NaN losses. CogView achieves the state-of-the-art FID on the blurred MS COCO dataset, outperforming previous GAN-based models and a r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.13290","kind":"arxiv","version":3},"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/2105.13290/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":"2026-07-05T03:29:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eApYsuUD+jYoL8AjPd2UuMytcsFl5taOCfPut3GMfuD8h78cbvBBdzj1hOUnm6Ne8YnE877X3z2P7fliQhtLBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T17:10:09.878368Z"},"content_sha256":"f31c0b3bbedefaa3e6c78680e5d24c830c8f0182aa10c40fab59bad1f54f35e8","schema_version":"1.0","event_id":"sha256:f31c0b3bbedefaa3e6c78680e5d24c830c8f0182aa10c40fab59bad1f54f35e8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZJWEOS4KOQBY34GROIURDHFPHR/bundle.json","state_url":"https://pith.science/pith/ZJWEOS4KOQBY34GROIURDHFPHR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZJWEOS4KOQBY34GROIURDHFPHR/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":"2026-08-19T17:10:09Z","links":{"resolver":"https://pith.science/pith/ZJWEOS4KOQBY34GROIURDHFPHR","bundle":"https://pith.science/pith/ZJWEOS4KOQBY34GROIURDHFPHR/bundle.json","state":"https://pith.science/pith/ZJWEOS4KOQBY34GROIURDHFPHR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZJWEOS4KOQBY34GROIURDHFPHR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ZJWEOS4KOQBY34GROIURDHFPHR","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":"ddb4aec60a1f95e4c42d0deba8ed79cc1124206a16e0fe87749942d575401e34","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-05-26T16:52:53Z","title_canon_sha256":"f3da52acf16e06ca3f4a328144e9b4eae244cc5d4004cc76eb08bb4efe3f8962"},"schema_version":"1.0","source":{"id":"2105.13290","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.13290","created_at":"2026-07-05T03:29:16Z"},{"alias_kind":"arxiv_version","alias_value":"2105.13290v3","created_at":"2026-07-05T03:29:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.13290","created_at":"2026-07-05T03:29:16Z"},{"alias_kind":"pith_short_12","alias_value":"ZJWEOS4KOQBY","created_at":"2026-07-05T03:29:16Z"},{"alias_kind":"pith_short_16","alias_value":"ZJWEOS4KOQBY34GR","created_at":"2026-07-05T03:29:16Z"},{"alias_kind":"pith_short_8","alias_value":"ZJWEOS4K","created_at":"2026-07-05T03:29:16Z"}],"graph_snapshots":[{"event_id":"sha256:f31c0b3bbedefaa3e6c78680e5d24c830c8f0182aa10c40fab59bad1f54f35e8","target":"graph","created_at":"2026-07-05T03:29:16Z","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/2105.13290/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-to-Image generation in the general domain has long been an open problem, which requires both a powerful generative model and cross-modal understanding. We propose CogView, a 4-billion-parameter Transformer with VQ-VAE tokenizer to advance this problem. We also demonstrate the finetuning strategies for various downstream tasks, e.g. style learning, super-resolution, text-image ranking and fashion design, and methods to stabilize pretraining, e.g. eliminating NaN losses. CogView achieves the state-of-the-art FID on the blurred MS COCO dataset, outperforming previous GAN-based models and a r","authors_text":"Chang Zhou, Da Yin, Hongxia Yang, Jie Tang, Junyang Lin, Ming Ding, Wendi Zheng, Wenyi Hong, Xu Zou, Zhou Shao, Zhuoyi Yang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-05-26T16:52:53Z","title":"CogView: Mastering Text-to-Image Generation via Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.13290","kind":"arxiv","version":3},"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":"sha256:3829002c28a2b99e82f1c865718ff50323225e931b5a82180d8445bfbc020999","target":"record","created_at":"2026-07-05T03:29:16Z","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":"ddb4aec60a1f95e4c42d0deba8ed79cc1124206a16e0fe87749942d575401e34","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-05-26T16:52:53Z","title_canon_sha256":"f3da52acf16e06ca3f4a328144e9b4eae244cc5d4004cc76eb08bb4efe3f8962"},"schema_version":"1.0","source":{"id":"2105.13290","kind":"arxiv","version":3}},"canonical_sha256":"ca6c474b8a74038df0d17229119caf3c73aa78b2c6871819407ad0b286a1f4b8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ca6c474b8a74038df0d17229119caf3c73aa78b2c6871819407ad0b286a1f4b8","first_computed_at":"2026-07-05T03:29:16.626252Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:29:16.626252Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eBfqu/FtewsN2jm1/aZTjQmIqvnyjEsEPD4twEOG+xDR4nALbdonFhNWSWrtlenqrOnkYiGl+55wnwJLZ2j1Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:29:16.626812Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.13290","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3829002c28a2b99e82f1c865718ff50323225e931b5a82180d8445bfbc020999","sha256:f31c0b3bbedefaa3e6c78680e5d24c830c8f0182aa10c40fab59bad1f54f35e8"],"state_sha256":"028428f8fab5f2f07625f190d8999676596be74960fb37cdb13eb4dc2dae6be8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Gpyy6hzXkmI8OHC1uNPfhIZjJqKo4BdlQilfoiDBjV8ASj+JfQsWRr3uSJRlEvQmhce/ik/C6+P6Om3pZTM8Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T17:10:09.883507Z","bundle_sha256":"9b18798f99a0407e22363aa5319c9bbcd0c24ebb964a25df7d9dbf0a4477239b"}}