{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:EMMXUCQBG66HLJ7OVHN7KSAIFO","short_pith_number":"pith:EMMXUCQB","schema_version":"1.0","canonical_sha256":"23197a0a0137bc75a7eea9dbf548082b8aa833185908a73bc06eef3ca3fabe59","source":{"kind":"arxiv","id":"2204.14217","version":2},"attestation_state":"computed","paper":{"title":"CogView2: Faster and Better Text-to-Image Generation via Hierarchical Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Jie Tang, Ming Ding, Wendi Zheng, Wenyi Hong","submitted_at":"2022-04-28T15:51:11Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2204.14217","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-28T15:51:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c8f151900ff64154cd5b5cb1c435aede9e99c2d7f287e312d56a5bfca97e1273","abstract_canon_sha256":"5bd996aa9448812a62472f32402aceb7a70fda0da0dcb9871424f3c1f1761971"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:26:49.239143Z","signature_b64":"1rcsOPngoB3NgBTSS7rl/JGQywG1nl64C16bQcNXQYxDFWlaxg8wYYrETcMwx/lIcZy3pkC7ZpmbnY/HYASKDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23197a0a0137bc75a7eea9dbf548082b8aa833185908a73bc06eef3ca3fabe59","last_reissued_at":"2026-07-05T04:26:49.238682Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:26:49.238682Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CogView2: Faster and Better Text-to-Image Generation via Hierarchical Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Jie Tang, Ming Ding, Wendi Zheng, Wenyi Hong","submitted_at":"2022-04-28T15:51:11Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.14217","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/2204.14217/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2204.14217","created_at":"2026-07-05T04:26:49.238743+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.14217v2","created_at":"2026-07-05T04:26:49.238743+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.14217","created_at":"2026-07-05T04:26:49.238743+00:00"},{"alias_kind":"pith_short_12","alias_value":"EMMXUCQBG66H","created_at":"2026-07-05T04:26:49.238743+00:00"},{"alias_kind":"pith_short_16","alias_value":"EMMXUCQBG66HLJ7O","created_at":"2026-07-05T04:26:49.238743+00:00"},{"alias_kind":"pith_short_8","alias_value":"EMMXUCQB","created_at":"2026-07-05T04:26:49.238743+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2308.08089","citing_title":"DragNUWA: Fine-grained Control in Video Generation by Integrating Text, Image, and Trajectory","ref_index":196,"is_internal_anchor":false},{"citing_arxiv_id":"2205.15868","citing_title":"CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2209.14792","citing_title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EMMXUCQBG66HLJ7OVHN7KSAIFO","json":"https://pith.science/pith/EMMXUCQBG66HLJ7OVHN7KSAIFO.json","graph_json":"https://pith.science/api/pith-number/EMMXUCQBG66HLJ7OVHN7KSAIFO/graph.json","events_json":"https://pith.science/api/pith-number/EMMXUCQBG66HLJ7OVHN7KSAIFO/events.json","paper":"https://pith.science/paper/EMMXUCQB"},"agent_actions":{"view_html":"https://pith.science/pith/EMMXUCQBG66HLJ7OVHN7KSAIFO","download_json":"https://pith.science/pith/EMMXUCQBG66HLJ7OVHN7KSAIFO.json","view_paper":"https://pith.science/paper/EMMXUCQB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.14217&json=true","fetch_graph":"https://pith.science/api/pith-number/EMMXUCQBG66HLJ7OVHN7KSAIFO/graph.json","fetch_events":"https://pith.science/api/pith-number/EMMXUCQBG66HLJ7OVHN7KSAIFO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EMMXUCQBG66HLJ7OVHN7KSAIFO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EMMXUCQBG66HLJ7OVHN7KSAIFO/action/storage_attestation","attest_author":"https://pith.science/pith/EMMXUCQBG66HLJ7OVHN7KSAIFO/action/author_attestation","sign_citation":"https://pith.science/pith/EMMXUCQBG66HLJ7OVHN7KSAIFO/action/citation_signature","submit_replication":"https://pith.science/pith/EMMXUCQBG66HLJ7OVHN7KSAIFO/action/replication_record"}},"created_at":"2026-07-05T04:26:49.238743+00:00","updated_at":"2026-07-05T04:26:49.238743+00:00"}