{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5QWGC4CGIT52Q6E2RBBCSB7R2M","short_pith_number":"pith:5QWGC4CG","schema_version":"1.0","canonical_sha256":"ec2c61704644fba8789a88422907f1d3218f104a9d9c472a49219e436c40d4bb","source":{"kind":"arxiv","id":"2312.03626","version":2},"attestation_state":"computed","paper":{"title":"TokenCompose: Text-to-Image Diffusion with Token-level Supervision","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Yilin Wang, Zheng Ding, Zhizhou Sha, Zhuowen Tu, Zirui Wang","submitted_at":"2023-12-06T17:13:15Z","abstract_excerpt":"We present TokenCompose, a Latent Diffusion Model for text-to-image generation that achieves enhanced consistency between user-specified text prompts and model-generated images. Despite its tremendous success, the standard denoising process in the Latent Diffusion Model takes text prompts as conditions only, absent explicit constraint for the consistency between the text prompts and the image contents, leading to unsatisfactory results for composing multiple object categories. TokenCompose aims to improve multi-category instance composition by introducing the token-wise consistency terms betwe"},"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":"2312.03626","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-06T17:13:15Z","cross_cats_sorted":[],"title_canon_sha256":"b66fa00aebdfafd3c6628fec22a2dba19ed3340e6d18c83686643b0c72499674","abstract_canon_sha256":"dcbe783899f672f3e1e47af6df531606d56a7b07c4a1bf6619903f29a5c55791"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:35:39.893217Z","signature_b64":"ckaFe34/ZVqfbTwPUUwdABSorujGeysXakKtLTzJNImU+xi/7iI0RY4IwB+821OWQMif1bxgL1yVX22I8PC9Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec2c61704644fba8789a88422907f1d3218f104a9d9c472a49219e436c40d4bb","last_reissued_at":"2026-07-05T08:35:39.892732Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:35:39.892732Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TokenCompose: Text-to-Image Diffusion with Token-level Supervision","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Yilin Wang, Zheng Ding, Zhizhou Sha, Zhuowen Tu, Zirui Wang","submitted_at":"2023-12-06T17:13:15Z","abstract_excerpt":"We present TokenCompose, a Latent Diffusion Model for text-to-image generation that achieves enhanced consistency between user-specified text prompts and model-generated images. Despite its tremendous success, the standard denoising process in the Latent Diffusion Model takes text prompts as conditions only, absent explicit constraint for the consistency between the text prompts and the image contents, leading to unsatisfactory results for composing multiple object categories. TokenCompose aims to improve multi-category instance composition by introducing the token-wise consistency terms betwe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.03626","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/2312.03626/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":"2312.03626","created_at":"2026-07-05T08:35:39.892792+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.03626v2","created_at":"2026-07-05T08:35:39.892792+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.03626","created_at":"2026-07-05T08:35:39.892792+00:00"},{"alias_kind":"pith_short_12","alias_value":"5QWGC4CGIT52","created_at":"2026-07-05T08:35:39.892792+00:00"},{"alias_kind":"pith_short_16","alias_value":"5QWGC4CGIT52Q6E2","created_at":"2026-07-05T08:35:39.892792+00:00"},{"alias_kind":"pith_short_8","alias_value":"5QWGC4CG","created_at":"2026-07-05T08:35:39.892792+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/5QWGC4CGIT52Q6E2RBBCSB7R2M","json":"https://pith.science/pith/5QWGC4CGIT52Q6E2RBBCSB7R2M.json","graph_json":"https://pith.science/api/pith-number/5QWGC4CGIT52Q6E2RBBCSB7R2M/graph.json","events_json":"https://pith.science/api/pith-number/5QWGC4CGIT52Q6E2RBBCSB7R2M/events.json","paper":"https://pith.science/paper/5QWGC4CG"},"agent_actions":{"view_html":"https://pith.science/pith/5QWGC4CGIT52Q6E2RBBCSB7R2M","download_json":"https://pith.science/pith/5QWGC4CGIT52Q6E2RBBCSB7R2M.json","view_paper":"https://pith.science/paper/5QWGC4CG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.03626&json=true","fetch_graph":"https://pith.science/api/pith-number/5QWGC4CGIT52Q6E2RBBCSB7R2M/graph.json","fetch_events":"https://pith.science/api/pith-number/5QWGC4CGIT52Q6E2RBBCSB7R2M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5QWGC4CGIT52Q6E2RBBCSB7R2M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5QWGC4CGIT52Q6E2RBBCSB7R2M/action/storage_attestation","attest_author":"https://pith.science/pith/5QWGC4CGIT52Q6E2RBBCSB7R2M/action/author_attestation","sign_citation":"https://pith.science/pith/5QWGC4CGIT52Q6E2RBBCSB7R2M/action/citation_signature","submit_replication":"https://pith.science/pith/5QWGC4CGIT52Q6E2RBBCSB7R2M/action/replication_record"}},"created_at":"2026-07-05T08:35:39.892792+00:00","updated_at":"2026-07-05T08:35:39.892792+00:00"}