{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XVAR5K6LPDUXZMAOCTBDIWP3CB","short_pith_number":"pith:XVAR5K6L","schema_version":"1.0","canonical_sha256":"bd411eabcb78e97cb00e14c23459fb10603c42b5632007cad7549491c27b8c63","source":{"kind":"arxiv","id":"2311.13620","version":1},"attestation_state":"computed","paper":{"title":"The Challenges of Image Generation Models in Generating Multi-Component Images","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Danilo Vasconcellos Vargas, Po Yuan Mao, Shashank Kotyan, Tham Yik Foong","submitted_at":"2023-11-22T07:18:41Z","abstract_excerpt":"Recent advances in text-to-image generators have led to substantial capabilities in image generation. However, the complexity of prompts acts as a bottleneck in the quality of images generated. A particular under-explored facet is the ability of generative models to create high-quality images comprising multiple components given as a prior. In this paper, we propose and validate a metric called Components Inclusion Score (CIS) to evaluate the extent to which a model can correctly generate multiple components. Our results reveal that the evaluated models struggle to incorporate all the visual e"},"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":"2311.13620","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-22T07:18:41Z","cross_cats_sorted":[],"title_canon_sha256":"3cc3d9d153768abb25646c742aa4d26a16a8abcc80d7deac57e392decd416f57","abstract_canon_sha256":"a13bf766edb10eb6981d3e565690d7efbc032f890367995f8735ddd89401fb14"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:16:05.492803Z","signature_b64":"lNM2YyFrP47+XUwJJJCXo7ucc33zHeQTYpoY503X66xXgeOp/DDhVbpcErRymTIA+C36f+5PF8TFEPN5lLRJAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd411eabcb78e97cb00e14c23459fb10603c42b5632007cad7549491c27b8c63","last_reissued_at":"2026-07-05T07:16:05.492290Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:16:05.492290Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Challenges of Image Generation Models in Generating Multi-Component Images","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Danilo Vasconcellos Vargas, Po Yuan Mao, Shashank Kotyan, Tham Yik Foong","submitted_at":"2023-11-22T07:18:41Z","abstract_excerpt":"Recent advances in text-to-image generators have led to substantial capabilities in image generation. However, the complexity of prompts acts as a bottleneck in the quality of images generated. A particular under-explored facet is the ability of generative models to create high-quality images comprising multiple components given as a prior. In this paper, we propose and validate a metric called Components Inclusion Score (CIS) to evaluate the extent to which a model can correctly generate multiple components. Our results reveal that the evaluated models struggle to incorporate all the visual e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.13620","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/2311.13620/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":"2311.13620","created_at":"2026-07-05T07:16:05.492365+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.13620v1","created_at":"2026-07-05T07:16:05.492365+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.13620","created_at":"2026-07-05T07:16:05.492365+00:00"},{"alias_kind":"pith_short_12","alias_value":"XVAR5K6LPDUX","created_at":"2026-07-05T07:16:05.492365+00:00"},{"alias_kind":"pith_short_16","alias_value":"XVAR5K6LPDUXZMAO","created_at":"2026-07-05T07:16:05.492365+00:00"},{"alias_kind":"pith_short_8","alias_value":"XVAR5K6L","created_at":"2026-07-05T07:16:05.492365+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07051","citing_title":"Making Implicit Preservation Intent Explicit in Conversational Image Editing","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XVAR5K6LPDUXZMAOCTBDIWP3CB","json":"https://pith.science/pith/XVAR5K6LPDUXZMAOCTBDIWP3CB.json","graph_json":"https://pith.science/api/pith-number/XVAR5K6LPDUXZMAOCTBDIWP3CB/graph.json","events_json":"https://pith.science/api/pith-number/XVAR5K6LPDUXZMAOCTBDIWP3CB/events.json","paper":"https://pith.science/paper/XVAR5K6L"},"agent_actions":{"view_html":"https://pith.science/pith/XVAR5K6LPDUXZMAOCTBDIWP3CB","download_json":"https://pith.science/pith/XVAR5K6LPDUXZMAOCTBDIWP3CB.json","view_paper":"https://pith.science/paper/XVAR5K6L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.13620&json=true","fetch_graph":"https://pith.science/api/pith-number/XVAR5K6LPDUXZMAOCTBDIWP3CB/graph.json","fetch_events":"https://pith.science/api/pith-number/XVAR5K6LPDUXZMAOCTBDIWP3CB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XVAR5K6LPDUXZMAOCTBDIWP3CB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XVAR5K6LPDUXZMAOCTBDIWP3CB/action/storage_attestation","attest_author":"https://pith.science/pith/XVAR5K6LPDUXZMAOCTBDIWP3CB/action/author_attestation","sign_citation":"https://pith.science/pith/XVAR5K6LPDUXZMAOCTBDIWP3CB/action/citation_signature","submit_replication":"https://pith.science/pith/XVAR5K6LPDUXZMAOCTBDIWP3CB/action/replication_record"}},"created_at":"2026-07-05T07:16:05.492365+00:00","updated_at":"2026-07-05T07:16:05.492365+00:00"}