{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:JP2RGUQRXPIZJOQAI6F7LDB7WI","short_pith_number":"pith:JP2RGUQR","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"},"canonical_sha256":"4bf5135211bbd194ba00478bf58c3fb23ed1483091c048a069b1e67646a288ff","source":{"kind":"arxiv","id":"2605.20640","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:JP2RGUQRXPIZJOQAI6F7LDB7WI","target":"record","payload":{"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"},"canonical_sha256":"4bf5135211bbd194ba00478bf58c3fb23ed1483091c048a069b1e67646a288ff","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"},"source_kind":"arxiv","source_id":"2605.20640","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-21T01:04:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AOj63G+Wpg5vnPtSmNIVudGmMjFKeZ2UCYLQa0Ni2c1lKU+hPmeXCXoRmN3D2IGqOSB5yHfnG7XOZwJzs9xrDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T21:57:03.719867Z"},"content_sha256":"02baea250c27b51535b91d7d6585eb8fdeddc40ea9372f43ef1cdab109d1ef8e","schema_version":"1.0","event_id":"sha256:02baea250c27b51535b91d7d6585eb8fdeddc40ea9372f43ef1cdab109d1ef8e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:JP2RGUQRXPIZJOQAI6F7LDB7WI","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-21T01:04:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6GH/wTCighbZf+SLmCZ5Ylz4XtbWf3rQjT+L1bbCxo/FOPZI8s8HotGT9j/TUQeUrp7t0F1Lzghu0uJc+AQVDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T21:57:03.720295Z"},"content_sha256":"732ff92f9647ec38837a44e8cb80324a70cd3fe1177dd21aa979ddc645733f0a","schema_version":"1.0","event_id":"sha256:732ff92f9647ec38837a44e8cb80324a70cd3fe1177dd21aa979ddc645733f0a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JP2RGUQRXPIZJOQAI6F7LDB7WI/bundle.json","state_url":"https://pith.science/pith/JP2RGUQRXPIZJOQAI6F7LDB7WI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JP2RGUQRXPIZJOQAI6F7LDB7WI/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-24T21:57:03Z","links":{"resolver":"https://pith.science/pith/JP2RGUQRXPIZJOQAI6F7LDB7WI","bundle":"https://pith.science/pith/JP2RGUQRXPIZJOQAI6F7LDB7WI/bundle.json","state":"https://pith.science/pith/JP2RGUQRXPIZJOQAI6F7LDB7WI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JP2RGUQRXPIZJOQAI6F7LDB7WI/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"23O6lQeoxf0jKltT/KHISU2Wd0wSVNrdR+d9tRK8q3GFXCQNq1S+jGh8uaIsB9w/S06Y9TSC5hsD4gXG9dMsBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-24T21:57:03.723645Z","bundle_sha256":"fa3e6e17b5943e5333539da5b27bb3235ec97301acc81c019110b317b7e4601f"}}