{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:AR72ILWQBSQBT7U5WLXYIRS4G2","short_pith_number":"pith:AR72ILWQ","schema_version":"1.0","canonical_sha256":"047fa42ed00ca019fe9db2ef84465c3691783574bfb275745f1880f9e1e42fd4","source":{"kind":"arxiv","id":"2108.08955","version":1},"attestation_state":"computed","paper":{"title":"CIGLI: Conditional Image Generation from Language & Image","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Hao Zhu, Jared Fernandez, Lynnette Ng, Xiaopeng Lu","submitted_at":"2021-08-20T00:58:42Z","abstract_excerpt":"Multi-modal generation has been widely explored in recent years. Current research directions involve generating text based on an image or vice versa. In this paper, we propose a new task called CIGLI: Conditional Image Generation from Language and Image. Instead of generating an image based on text as in text-image generation, this task requires the generation of an image from a textual description and an image prompt. We designed a new dataset to ensure that the text description describes information from both images, and that solely analyzing the description is insufficient to generate an im"},"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":"2108.08955","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-08-20T00:58:42Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"ae53890fdada67ce807a7d8a4521f2627df693cfeb62e6d17cd510d828216ed7","abstract_canon_sha256":"9d53eecc32be643fb13f4a950aef04a90d06232f49e7ddc740f70c320cfdebe5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:07:32.260542Z","signature_b64":"AfL4z5Sj2OGSBluYZp1fYZN35UOrOrUsP9OKcocQQaVOD8mpRVotJgNjqBoIlTTWhZ+6WWIkLKb7eYWbz2WIDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"047fa42ed00ca019fe9db2ef84465c3691783574bfb275745f1880f9e1e42fd4","last_reissued_at":"2026-07-05T03:07:32.260188Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:07:32.260188Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CIGLI: Conditional Image Generation from Language & Image","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Hao Zhu, Jared Fernandez, Lynnette Ng, Xiaopeng Lu","submitted_at":"2021-08-20T00:58:42Z","abstract_excerpt":"Multi-modal generation has been widely explored in recent years. Current research directions involve generating text based on an image or vice versa. In this paper, we propose a new task called CIGLI: Conditional Image Generation from Language and Image. Instead of generating an image based on text as in text-image generation, this task requires the generation of an image from a textual description and an image prompt. We designed a new dataset to ensure that the text description describes information from both images, and that solely analyzing the description is insufficient to generate an im"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.08955","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/2108.08955/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":"2108.08955","created_at":"2026-07-05T03:07:32.260238+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.08955v1","created_at":"2026-07-05T03:07:32.260238+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.08955","created_at":"2026-07-05T03:07:32.260238+00:00"},{"alias_kind":"pith_short_12","alias_value":"AR72ILWQBSQB","created_at":"2026-07-05T03:07:32.260238+00:00"},{"alias_kind":"pith_short_16","alias_value":"AR72ILWQBSQBT7U5","created_at":"2026-07-05T03:07:32.260238+00:00"},{"alias_kind":"pith_short_8","alias_value":"AR72ILWQ","created_at":"2026-07-05T03:07:32.260238+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/AR72ILWQBSQBT7U5WLXYIRS4G2","json":"https://pith.science/pith/AR72ILWQBSQBT7U5WLXYIRS4G2.json","graph_json":"https://pith.science/api/pith-number/AR72ILWQBSQBT7U5WLXYIRS4G2/graph.json","events_json":"https://pith.science/api/pith-number/AR72ILWQBSQBT7U5WLXYIRS4G2/events.json","paper":"https://pith.science/paper/AR72ILWQ"},"agent_actions":{"view_html":"https://pith.science/pith/AR72ILWQBSQBT7U5WLXYIRS4G2","download_json":"https://pith.science/pith/AR72ILWQBSQBT7U5WLXYIRS4G2.json","view_paper":"https://pith.science/paper/AR72ILWQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.08955&json=true","fetch_graph":"https://pith.science/api/pith-number/AR72ILWQBSQBT7U5WLXYIRS4G2/graph.json","fetch_events":"https://pith.science/api/pith-number/AR72ILWQBSQBT7U5WLXYIRS4G2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AR72ILWQBSQBT7U5WLXYIRS4G2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AR72ILWQBSQBT7U5WLXYIRS4G2/action/storage_attestation","attest_author":"https://pith.science/pith/AR72ILWQBSQBT7U5WLXYIRS4G2/action/author_attestation","sign_citation":"https://pith.science/pith/AR72ILWQBSQBT7U5WLXYIRS4G2/action/citation_signature","submit_replication":"https://pith.science/pith/AR72ILWQBSQBT7U5WLXYIRS4G2/action/replication_record"}},"created_at":"2026-07-05T03:07:32.260238+00:00","updated_at":"2026-07-05T03:07:32.260238+00:00"}