{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LGHKWXXZNITYFE6KFN46Z7HLMJ","short_pith_number":"pith:LGHKWXXZ","schema_version":"1.0","canonical_sha256":"598eab5ef96a278293ca2b79ecfceb625e588ea9e2dd6c0bf8f4b74166d4a17f","source":{"kind":"arxiv","id":"2408.00230","version":2},"attestation_state":"computed","paper":{"title":"Lost in Translation: Latent Concept Misalignment in Text-to-Image Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Chongxuan Li, Dequan Wang, Juntu Zhao, Junyu Deng, Yixin Ye, Zhijie Deng","submitted_at":"2024-08-01T01:54:17Z","abstract_excerpt":"Advancements in text-to-image diffusion models have broadened extensive downstream practical applications, but such models often encounter misalignment issues between text and image. Taking the generation of a combination of two disentangled concepts as an example, say given the prompt \"a tea cup of iced coke\", existing models usually generate a glass cup of iced coke because the iced coke usually co-occurs with the glass cup instead of the tea one during model training. The root of such misalignment is attributed to the confusion in the latent semantic space of text-to-image diffusion models,"},"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":"2408.00230","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-08-01T01:54:17Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"efe6d787fd8873c61ac4752cddcdeeb074fdc604ca8d7adaf631c5a0f801c75b","abstract_canon_sha256":"982b64370d9cb21fffd537585709144fdddbaf0a2ce1acc0d397f449e5f7034a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:51:57.134358Z","signature_b64":"fur53moMWhXjVjVXoLhPB6zElMitfkIKiv3+DvbdMF/UQh7sqxYm+g+MX/U0vIigYQOjSuAXQsaJK+3wXKmNCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"598eab5ef96a278293ca2b79ecfceb625e588ea9e2dd6c0bf8f4b74166d4a17f","last_reissued_at":"2026-07-05T08:51:57.133878Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:51:57.133878Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lost in Translation: Latent Concept Misalignment in Text-to-Image Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Chongxuan Li, Dequan Wang, Juntu Zhao, Junyu Deng, Yixin Ye, Zhijie Deng","submitted_at":"2024-08-01T01:54:17Z","abstract_excerpt":"Advancements in text-to-image diffusion models have broadened extensive downstream practical applications, but such models often encounter misalignment issues between text and image. Taking the generation of a combination of two disentangled concepts as an example, say given the prompt \"a tea cup of iced coke\", existing models usually generate a glass cup of iced coke because the iced coke usually co-occurs with the glass cup instead of the tea one during model training. The root of such misalignment is attributed to the confusion in the latent semantic space of text-to-image diffusion models,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.00230","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/2408.00230/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":"2408.00230","created_at":"2026-07-05T08:51:57.133936+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.00230v2","created_at":"2026-07-05T08:51:57.133936+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.00230","created_at":"2026-07-05T08:51:57.133936+00:00"},{"alias_kind":"pith_short_12","alias_value":"LGHKWXXZNITY","created_at":"2026-07-05T08:51:57.133936+00:00"},{"alias_kind":"pith_short_16","alias_value":"LGHKWXXZNITYFE6K","created_at":"2026-07-05T08:51:57.133936+00:00"},{"alias_kind":"pith_short_8","alias_value":"LGHKWXXZ","created_at":"2026-07-05T08:51:57.133936+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.05080","citing_title":"Nidus: Externalized Reasoning for AI-Assisted Engineering","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LGHKWXXZNITYFE6KFN46Z7HLMJ","json":"https://pith.science/pith/LGHKWXXZNITYFE6KFN46Z7HLMJ.json","graph_json":"https://pith.science/api/pith-number/LGHKWXXZNITYFE6KFN46Z7HLMJ/graph.json","events_json":"https://pith.science/api/pith-number/LGHKWXXZNITYFE6KFN46Z7HLMJ/events.json","paper":"https://pith.science/paper/LGHKWXXZ"},"agent_actions":{"view_html":"https://pith.science/pith/LGHKWXXZNITYFE6KFN46Z7HLMJ","download_json":"https://pith.science/pith/LGHKWXXZNITYFE6KFN46Z7HLMJ.json","view_paper":"https://pith.science/paper/LGHKWXXZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.00230&json=true","fetch_graph":"https://pith.science/api/pith-number/LGHKWXXZNITYFE6KFN46Z7HLMJ/graph.json","fetch_events":"https://pith.science/api/pith-number/LGHKWXXZNITYFE6KFN46Z7HLMJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LGHKWXXZNITYFE6KFN46Z7HLMJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LGHKWXXZNITYFE6KFN46Z7HLMJ/action/storage_attestation","attest_author":"https://pith.science/pith/LGHKWXXZNITYFE6KFN46Z7HLMJ/action/author_attestation","sign_citation":"https://pith.science/pith/LGHKWXXZNITYFE6KFN46Z7HLMJ/action/citation_signature","submit_replication":"https://pith.science/pith/LGHKWXXZNITYFE6KFN46Z7HLMJ/action/replication_record"}},"created_at":"2026-07-05T08:51:57.133936+00:00","updated_at":"2026-07-05T08:51:57.133936+00:00"}