{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:TDP36K2LUR3AIY6HV4SIZCFI43","short_pith_number":"pith:TDP36K2L","schema_version":"1.0","canonical_sha256":"98dfbf2b4ba4760463c7af248c88a8e6c3c50d69aff7c567e3cf3c95ce62d86b","source":{"kind":"arxiv","id":"2111.09267","version":1},"attestation_state":"computed","paper":{"title":"DiverGAN: An Efficient and Effective Single-Stage Framework for Diverse Text-to-Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Lambert Schomaker, Zhenxing Zhang","submitted_at":"2021-11-17T17:59:56Z","abstract_excerpt":"In this paper, we present an efficient and effective single-stage framework (DiverGAN) to generate diverse, plausible and semantically consistent images according to a natural-language description. DiverGAN adopts two novel word-level attention modules, i.e., a channel-attention module (CAM) and a pixel-attention module (PAM), which model the importance of each word in the given sentence while allowing the network to assign larger weights to the significant channels and pixels semantically aligning with the salient words. After that, Conditional Adaptive Instance-Layer Normalization (CAdaILN) "},"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":"2111.09267","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-17T17:59:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"de0589bc3b317860b0716e1db299625b1a89820642d96dd1f9cb418aab9eec6f","abstract_canon_sha256":"0c439b5f2724cd6f9341a72a2155eab5367157cc53152aea009102b2b8334595"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:21:07.296963Z","signature_b64":"8WY1N8EEkZ8XEZzWPf4iZrCO7voXrdvNtSKKB3hhc9VDh2ivmCXPtUEB6PKTP0sKqmkwq0mjIeuEP6HEQSTlAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"98dfbf2b4ba4760463c7af248c88a8e6c3c50d69aff7c567e3cf3c95ce62d86b","last_reissued_at":"2026-07-05T04:21:07.296544Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:21:07.296544Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DiverGAN: An Efficient and Effective Single-Stage Framework for Diverse Text-to-Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Lambert Schomaker, Zhenxing Zhang","submitted_at":"2021-11-17T17:59:56Z","abstract_excerpt":"In this paper, we present an efficient and effective single-stage framework (DiverGAN) to generate diverse, plausible and semantically consistent images according to a natural-language description. DiverGAN adopts two novel word-level attention modules, i.e., a channel-attention module (CAM) and a pixel-attention module (PAM), which model the importance of each word in the given sentence while allowing the network to assign larger weights to the significant channels and pixels semantically aligning with the salient words. After that, Conditional Adaptive Instance-Layer Normalization (CAdaILN) "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.09267","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2111.09267/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":"2111.09267","created_at":"2026-07-05T04:21:07.296606+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.09267v1","created_at":"2026-07-05T04:21:07.296606+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.09267","created_at":"2026-07-05T04:21:07.296606+00:00"},{"alias_kind":"pith_short_12","alias_value":"TDP36K2LUR3A","created_at":"2026-07-05T04:21:07.296606+00:00"},{"alias_kind":"pith_short_16","alias_value":"TDP36K2LUR3AIY6H","created_at":"2026-07-05T04:21:07.296606+00:00"},{"alias_kind":"pith_short_8","alias_value":"TDP36K2L","created_at":"2026-07-05T04:21:07.296606+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TDP36K2LUR3AIY6HV4SIZCFI43","json":"https://pith.science/pith/TDP36K2LUR3AIY6HV4SIZCFI43.json","graph_json":"https://pith.science/api/pith-number/TDP36K2LUR3AIY6HV4SIZCFI43/graph.json","events_json":"https://pith.science/api/pith-number/TDP36K2LUR3AIY6HV4SIZCFI43/events.json","paper":"https://pith.science/paper/TDP36K2L"},"agent_actions":{"view_html":"https://pith.science/pith/TDP36K2LUR3AIY6HV4SIZCFI43","download_json":"https://pith.science/pith/TDP36K2LUR3AIY6HV4SIZCFI43.json","view_paper":"https://pith.science/paper/TDP36K2L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.09267&json=true","fetch_graph":"https://pith.science/api/pith-number/TDP36K2LUR3AIY6HV4SIZCFI43/graph.json","fetch_events":"https://pith.science/api/pith-number/TDP36K2LUR3AIY6HV4SIZCFI43/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TDP36K2LUR3AIY6HV4SIZCFI43/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TDP36K2LUR3AIY6HV4SIZCFI43/action/storage_attestation","attest_author":"https://pith.science/pith/TDP36K2LUR3AIY6HV4SIZCFI43/action/author_attestation","sign_citation":"https://pith.science/pith/TDP36K2LUR3AIY6HV4SIZCFI43/action/citation_signature","submit_replication":"https://pith.science/pith/TDP36K2LUR3AIY6HV4SIZCFI43/action/replication_record"}},"created_at":"2026-07-05T04:21:07.296606+00:00","updated_at":"2026-07-05T04:21:07.296606+00:00"}