{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:EMMXUCQBG66HLJ7OVHN7KSAIFO","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":"5bd996aa9448812a62472f32402aceb7a70fda0da0dcb9871424f3c1f1761971","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-28T15:51:11Z","title_canon_sha256":"c8f151900ff64154cd5b5cb1c435aede9e99c2d7f287e312d56a5bfca97e1273"},"schema_version":"1.0","source":{"id":"2204.14217","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.14217","created_at":"2026-07-05T04:26:49Z"},{"alias_kind":"arxiv_version","alias_value":"2204.14217v2","created_at":"2026-07-05T04:26:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.14217","created_at":"2026-07-05T04:26:49Z"},{"alias_kind":"pith_short_12","alias_value":"EMMXUCQBG66H","created_at":"2026-07-05T04:26:49Z"},{"alias_kind":"pith_short_16","alias_value":"EMMXUCQBG66HLJ7O","created_at":"2026-07-05T04:26:49Z"},{"alias_kind":"pith_short_8","alias_value":"EMMXUCQB","created_at":"2026-07-05T04:26:49Z"}],"graph_snapshots":[{"event_id":"sha256:bd7f9a106ad8adad35f97ce53646394d902a2f94b7f6b7b745c0c08fb3919e38","target":"graph","created_at":"2026-07-05T04:26:49Z","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/2204.14217/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The development of the transformer-based text-to-image models are impeded by its slow generation and complexity for high-resolution images. In this work, we put forward a solution based on hierarchical transformers and local parallel auto-regressive generation. We pretrain a 6B-parameter transformer with a simple and flexible self-supervised task, Cross-modal general language model (CogLM), and finetune it for fast super-resolution. The new text-to-image system, CogView2, shows very competitive generation compared to concurrent state-of-the-art DALL-E-2, and naturally supports interactive text","authors_text":"Jie Tang, Ming Ding, Wendi Zheng, Wenyi Hong","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-28T15:51:11Z","title":"CogView2: Faster and Better Text-to-Image Generation via Hierarchical Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.14217","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":"sha256:167e7285688f4bf7ea7a4cf958c8956edbca9259c5c775c75011a71d4581c46f","target":"record","created_at":"2026-07-05T04:26:49Z","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":"5bd996aa9448812a62472f32402aceb7a70fda0da0dcb9871424f3c1f1761971","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-28T15:51:11Z","title_canon_sha256":"c8f151900ff64154cd5b5cb1c435aede9e99c2d7f287e312d56a5bfca97e1273"},"schema_version":"1.0","source":{"id":"2204.14217","kind":"arxiv","version":2}},"canonical_sha256":"23197a0a0137bc75a7eea9dbf548082b8aa833185908a73bc06eef3ca3fabe59","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"23197a0a0137bc75a7eea9dbf548082b8aa833185908a73bc06eef3ca3fabe59","first_computed_at":"2026-07-05T04:26:49.238682Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:26:49.238682Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1rcsOPngoB3NgBTSS7rl/JGQywG1nl64C16bQcNXQYxDFWlaxg8wYYrETcMwx/lIcZy3pkC7ZpmbnY/HYASKDw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:26:49.239143Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.14217","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:167e7285688f4bf7ea7a4cf958c8956edbca9259c5c775c75011a71d4581c46f","sha256:bd7f9a106ad8adad35f97ce53646394d902a2f94b7f6b7b745c0c08fb3919e38"],"state_sha256":"cd53d30ad6b49542dfd3a4597e5f30a7c99033de8de9031e4a0b7286f9e09c27"}