{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AP3A5CXRPDGWFZKOYTZ2L5VF3L","short_pith_number":"pith:AP3A5CXR","schema_version":"1.0","canonical_sha256":"03f60e8af178cd62e54ec4f3a5f6a5dac41df700cdb80fe7f5238a39978ede19","source":{"kind":"arxiv","id":"2502.12579","version":3},"attestation_state":"computed","paper":{"title":"CHATS: Combining Human-Aligned Optimization and Test-Time Sampling for Text-to-Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guo-Hua Wang, Kaifu Zhang, Liangfu Cao, Minghao Fu, Qing-Guo Chen, Weihua Luo, Zhao Xu","submitted_at":"2025-02-18T06:31:08Z","abstract_excerpt":"Diffusion models have emerged as a dominant approach for text-to-image generation. Key components such as the human preference alignment and classifier-free guidance play a crucial role in ensuring generation quality. However, their independent application in current text-to-image models continues to face significant challenges in achieving strong text-image alignment, high generation quality, and consistency with human aesthetic standards. In this work, we for the first time, explore facilitating the collaboration of human performance alignment and test-time sampling to unlock the potential o"},"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":"2502.12579","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-18T06:31:08Z","cross_cats_sorted":[],"title_canon_sha256":"4df5cfe1bdeb39d389cf85d7a302625d9e4d0bc8415146dc665bf5e2f48b53ef","abstract_canon_sha256":"2023168a162ffd7555b0aad2d39f9fa4a88ba3d09abb4084130df344fd090118"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:41.473913Z","signature_b64":"HRbI8cpzdWOqIk5R+CYrFNuZpEmdisG3NKucT5CARB4vnOf2h98uZxZlEm+Q9vqYoepQEitOE2b5Qhb2J/sNAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03f60e8af178cd62e54ec4f3a5f6a5dac41df700cdb80fe7f5238a39978ede19","last_reissued_at":"2026-07-05T11:17:41.473394Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:41.473394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CHATS: Combining Human-Aligned Optimization and Test-Time Sampling for Text-to-Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guo-Hua Wang, Kaifu Zhang, Liangfu Cao, Minghao Fu, Qing-Guo Chen, Weihua Luo, Zhao Xu","submitted_at":"2025-02-18T06:31:08Z","abstract_excerpt":"Diffusion models have emerged as a dominant approach for text-to-image generation. Key components such as the human preference alignment and classifier-free guidance play a crucial role in ensuring generation quality. However, their independent application in current text-to-image models continues to face significant challenges in achieving strong text-image alignment, high generation quality, and consistency with human aesthetic standards. In this work, we for the first time, explore facilitating the collaboration of human performance alignment and test-time sampling to unlock the potential o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.12579","kind":"arxiv","version":3},"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/2502.12579/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":"2502.12579","created_at":"2026-07-05T11:17:41.473458+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.12579v3","created_at":"2026-07-05T11:17:41.473458+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.12579","created_at":"2026-07-05T11:17:41.473458+00:00"},{"alias_kind":"pith_short_12","alias_value":"AP3A5CXRPDGW","created_at":"2026-07-05T11:17:41.473458+00:00"},{"alias_kind":"pith_short_16","alias_value":"AP3A5CXRPDGWFZKO","created_at":"2026-07-05T11:17:41.473458+00:00"},{"alias_kind":"pith_short_8","alias_value":"AP3A5CXR","created_at":"2026-07-05T11:17:41.473458+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.09433","citing_title":"Offline Preference Optimization for Rectified Flow with Noise-Tracked Pairs","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AP3A5CXRPDGWFZKOYTZ2L5VF3L","json":"https://pith.science/pith/AP3A5CXRPDGWFZKOYTZ2L5VF3L.json","graph_json":"https://pith.science/api/pith-number/AP3A5CXRPDGWFZKOYTZ2L5VF3L/graph.json","events_json":"https://pith.science/api/pith-number/AP3A5CXRPDGWFZKOYTZ2L5VF3L/events.json","paper":"https://pith.science/paper/AP3A5CXR"},"agent_actions":{"view_html":"https://pith.science/pith/AP3A5CXRPDGWFZKOYTZ2L5VF3L","download_json":"https://pith.science/pith/AP3A5CXRPDGWFZKOYTZ2L5VF3L.json","view_paper":"https://pith.science/paper/AP3A5CXR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.12579&json=true","fetch_graph":"https://pith.science/api/pith-number/AP3A5CXRPDGWFZKOYTZ2L5VF3L/graph.json","fetch_events":"https://pith.science/api/pith-number/AP3A5CXRPDGWFZKOYTZ2L5VF3L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AP3A5CXRPDGWFZKOYTZ2L5VF3L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AP3A5CXRPDGWFZKOYTZ2L5VF3L/action/storage_attestation","attest_author":"https://pith.science/pith/AP3A5CXRPDGWFZKOYTZ2L5VF3L/action/author_attestation","sign_citation":"https://pith.science/pith/AP3A5CXRPDGWFZKOYTZ2L5VF3L/action/citation_signature","submit_replication":"https://pith.science/pith/AP3A5CXRPDGWFZKOYTZ2L5VF3L/action/replication_record"}},"created_at":"2026-07-05T11:17:41.473458+00:00","updated_at":"2026-07-05T11:17:41.473458+00:00"}