{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JP2RGUQRXPIZJOQAI6F7LDB7WI","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"65c535b410bbbd9176493d14dd400443822290a10c783df4f35425fa1883695c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-20T02:55:28Z","title_canon_sha256":"486687e7832789453eda534e3c631c3fbd46b232fef1eaeacac1941dca673ceb"},"schema_version":"1.0","source":{"id":"2605.20640","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.20640","created_at":"2026-05-21T01:04:46Z"},{"alias_kind":"arxiv_version","alias_value":"2605.20640v1","created_at":"2026-05-21T01:04:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20640","created_at":"2026-05-21T01:04:46Z"},{"alias_kind":"pith_short_12","alias_value":"JP2RGUQRXPIZ","created_at":"2026-05-21T01:04:46Z"},{"alias_kind":"pith_short_16","alias_value":"JP2RGUQRXPIZJOQA","created_at":"2026-05-21T01:04:46Z"},{"alias_kind":"pith_short_8","alias_value":"JP2RGUQR","created_at":"2026-05-21T01:04:46Z"}],"graph_snapshots":[{"event_id":"sha256:732ff92f9647ec38837a44e8cb80324a70cd3fe1177dd21aa979ddc645733f0a","target":"graph","created_at":"2026-05-21T01:04:46Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2605.20640/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jinjin Shi, Runyu Shi, Wenbin Gao, Xuran Xu, Ying Huang, Yunlong Wang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-20T02:55:28Z","title":"Pareto-Enhanced Portrait Generation: Vision-Aligned Text Supervision for Alignment, Realism, and Aesthetics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20640","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:02baea250c27b51535b91d7d6585eb8fdeddc40ea9372f43ef1cdab109d1ef8e","target":"record","created_at":"2026-05-21T01:04:46Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"65c535b410bbbd9176493d14dd400443822290a10c783df4f35425fa1883695c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-20T02:55:28Z","title_canon_sha256":"486687e7832789453eda534e3c631c3fbd46b232fef1eaeacac1941dca673ceb"},"schema_version":"1.0","source":{"id":"2605.20640","kind":"arxiv","version":1}},"canonical_sha256":"4bf5135211bbd194ba00478bf58c3fb23ed1483091c048a069b1e67646a288ff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4bf5135211bbd194ba00478bf58c3fb23ed1483091c048a069b1e67646a288ff","first_computed_at":"2026-05-21T01:04:46.312630Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T01:04:46.312630Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6HI0ZRR9VBKl8fxRauYNkCi5hq7jaOBTP32pmeb950hHc+Ut2xiYf+3Wnw8IWkTXejcHADrtvuP/n/H27U8rAA==","signature_status":"signed_v1","signed_at":"2026-05-21T01:04:46.313248Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.20640","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:02baea250c27b51535b91d7d6585eb8fdeddc40ea9372f43ef1cdab109d1ef8e","sha256:732ff92f9647ec38837a44e8cb80324a70cd3fe1177dd21aa979ddc645733f0a"],"state_sha256":"0a06f82a734c643c04c2ce3825868897937aeae0f56393a17858916489173a18"}