{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JP2RGUQRXPIZJOQAI6F7LDB7WI","short_pith_number":"pith:JP2RGUQR","schema_version":"1.0","canonical_sha256":"4bf5135211bbd194ba00478bf58c3fb23ed1483091c048a069b1e67646a288ff","source":{"kind":"arxiv","id":"2605.20640","version":1},"attestation_state":"computed","paper":{"title":"Pareto-Enhanced Portrait Generation: Vision-Aligned Text Supervision for Alignment, Realism, and Aesthetics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jinjin Shi, Runyu Shi, Wenbin Gao, Xuran Xu, Ying Huang, Yunlong Wang","submitted_at":"2026-05-20T02:55:28Z","abstract_excerpt":"Text-to-image diffusion models often face a severe trilemma in human portrait generation: text-image alignment, photorealism, and human-perceived aesthetics inherently inhibit one another. Supervised Fine-Tuning (SFT) is an effective method for enhancing the photorealism of image generation. However, it often leads to overfitting to the training dataset, corrupts pre-trained image priors, and degrades alignment or aesthetics. To break this bottleneck, we propose a feature supervision paradigm for Multimodal Diffusion Transformers (MM-DiT). Specifically, we introduce a lightweight cross-modal a"},"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":"2605.20640","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-20T02:55:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"486687e7832789453eda534e3c631c3fbd46b232fef1eaeacac1941dca673ceb","abstract_canon_sha256":"65c535b410bbbd9176493d14dd400443822290a10c783df4f35425fa1883695c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:04:46.313248Z","signature_b64":"6HI0ZRR9VBKl8fxRauYNkCi5hq7jaOBTP32pmeb950hHc+Ut2xiYf+3Wnw8IWkTXejcHADrtvuP/n/H27U8rAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4bf5135211bbd194ba00478bf58c3fb23ed1483091c048a069b1e67646a288ff","last_reissued_at":"2026-05-21T01:04:46.312630Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:04:46.312630Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pareto-Enhanced Portrait Generation: Vision-Aligned Text Supervision for Alignment, Realism, and Aesthetics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jinjin Shi, Runyu Shi, Wenbin Gao, Xuran Xu, Ying Huang, Yunlong Wang","submitted_at":"2026-05-20T02:55:28Z","abstract_excerpt":"Text-to-image diffusion models often face a severe trilemma in human portrait generation: text-image alignment, photorealism, and human-perceived aesthetics inherently inhibit one another. Supervised Fine-Tuning (SFT) is an effective method for enhancing the photorealism of image generation. However, it often leads to overfitting to the training dataset, corrupts pre-trained image priors, and degrades alignment or aesthetics. To break this bottleneck, we propose a feature supervision paradigm for Multimodal Diffusion Transformers (MM-DiT). Specifically, we introduce a lightweight cross-modal a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20640","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/2605.20640/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":"2605.20640","created_at":"2026-05-21T01:04:46.312712+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.20640v1","created_at":"2026-05-21T01:04:46.312712+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20640","created_at":"2026-05-21T01:04:46.312712+00:00"},{"alias_kind":"pith_short_12","alias_value":"JP2RGUQRXPIZ","created_at":"2026-05-21T01:04:46.312712+00:00"},{"alias_kind":"pith_short_16","alias_value":"JP2RGUQRXPIZJOQA","created_at":"2026-05-21T01:04:46.312712+00:00"},{"alias_kind":"pith_short_8","alias_value":"JP2RGUQR","created_at":"2026-05-21T01:04:46.312712+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/JP2RGUQRXPIZJOQAI6F7LDB7WI","json":"https://pith.science/pith/JP2RGUQRXPIZJOQAI6F7LDB7WI.json","graph_json":"https://pith.science/api/pith-number/JP2RGUQRXPIZJOQAI6F7LDB7WI/graph.json","events_json":"https://pith.science/api/pith-number/JP2RGUQRXPIZJOQAI6F7LDB7WI/events.json","paper":"https://pith.science/paper/JP2RGUQR"},"agent_actions":{"view_html":"https://pith.science/pith/JP2RGUQRXPIZJOQAI6F7LDB7WI","download_json":"https://pith.science/pith/JP2RGUQRXPIZJOQAI6F7LDB7WI.json","view_paper":"https://pith.science/paper/JP2RGUQR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.20640&json=true","fetch_graph":"https://pith.science/api/pith-number/JP2RGUQRXPIZJOQAI6F7LDB7WI/graph.json","fetch_events":"https://pith.science/api/pith-number/JP2RGUQRXPIZJOQAI6F7LDB7WI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JP2RGUQRXPIZJOQAI6F7LDB7WI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JP2RGUQRXPIZJOQAI6F7LDB7WI/action/storage_attestation","attest_author":"https://pith.science/pith/JP2RGUQRXPIZJOQAI6F7LDB7WI/action/author_attestation","sign_citation":"https://pith.science/pith/JP2RGUQRXPIZJOQAI6F7LDB7WI/action/citation_signature","submit_replication":"https://pith.science/pith/JP2RGUQRXPIZJOQAI6F7LDB7WI/action/replication_record"}},"created_at":"2026-05-21T01:04:46.312712+00:00","updated_at":"2026-05-21T01:04:46.312712+00:00"}