{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:TLK4TGR4ADTRWRLLDJQHOGWBP6","short_pith_number":"pith:TLK4TGR4","canonical_record":{"source":{"id":"2504.18204","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-25T09:35:02Z","cross_cats_sorted":[],"title_canon_sha256":"114343302d681a6ed9bdc1f2fe4bccfee555a6d4da62c44943dcab936f381434","abstract_canon_sha256":"2c34e2a70d4b89641499d5ed29ca817e4b4d209b512f7431db8c68db9bcddb29"},"schema_version":"1.0"},"canonical_sha256":"9ad5c99a3c00e71b456b1a60771ac17f9de5222d285baf19dc6cc6d09dd06fe8","source":{"kind":"arxiv","id":"2504.18204","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.18204","created_at":"2026-07-05T10:54:03Z"},{"alias_kind":"arxiv_version","alias_value":"2504.18204v1","created_at":"2026-07-05T10:54:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.18204","created_at":"2026-07-05T10:54:03Z"},{"alias_kind":"pith_short_12","alias_value":"TLK4TGR4ADTR","created_at":"2026-07-05T10:54:03Z"},{"alias_kind":"pith_short_16","alias_value":"TLK4TGR4ADTRWRLL","created_at":"2026-07-05T10:54:03Z"},{"alias_kind":"pith_short_8","alias_value":"TLK4TGR4","created_at":"2026-07-05T10:54:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:TLK4TGR4ADTRWRLLDJQHOGWBP6","target":"record","payload":{"canonical_record":{"source":{"id":"2504.18204","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-25T09:35:02Z","cross_cats_sorted":[],"title_canon_sha256":"114343302d681a6ed9bdc1f2fe4bccfee555a6d4da62c44943dcab936f381434","abstract_canon_sha256":"2c34e2a70d4b89641499d5ed29ca817e4b4d209b512f7431db8c68db9bcddb29"},"schema_version":"1.0"},"canonical_sha256":"9ad5c99a3c00e71b456b1a60771ac17f9de5222d285baf19dc6cc6d09dd06fe8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:54:03.678525Z","signature_b64":"byEPMgvad59BDn356vz3AhabGYPS00R3p71QwaL0P2rOnw0DDGErHoQ60R7nvUk68loEuLHg3w1Mc4N32f2PAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ad5c99a3c00e71b456b1a60771ac17f9de5222d285baf19dc6cc6d09dd06fe8","last_reissued_at":"2026-07-05T10:54:03.678059Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:54:03.678059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.18204","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":"2026-07-05T10:54:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VZrl4EBCiZAQYbBaIGxq0ftWtmbJgcddeSpcZfi17CgfdLeEcHbg8ydJLFedyFYGYS875uSWnWlGdkJfV+luAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T13:48:18.917543Z"},"content_sha256":"d26d5b9a5c8fef1836a6791c7f2b33ba4f386280309b4d11d58844392e2fcbf7","schema_version":"1.0","event_id":"sha256:d26d5b9a5c8fef1836a6791c7f2b33ba4f386280309b4d11d58844392e2fcbf7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:TLK4TGR4ADTRWRLLDJQHOGWBP6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Optimizing Multi-Round Enhanced Training in Diffusion Models for Improved Preference Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongyang He, Jianhui Wang, Jiaqi Chen, Keqin Li, Kun Li, Miao Zhang, Ruoyu Wang, Sida Li, Tianyu Shi, Wenxin Zhang, Xinyuan Song, Xueqian Wang, Yangfan He","submitted_at":"2025-04-25T09:35:02Z","abstract_excerpt":"Generative AI has significantly changed industries by enabling text-driven image generation, yet challenges remain in achieving high-resolution outputs that align with fine-grained user preferences. Consequently, multi-round interactions are necessary to ensure the generated images meet expectations. Previous methods enhanced prompts via reward feedback but did not optimize over a multi-round dialogue dataset. In this work, we present a Visual Co-Adaptation (VCA) framework incorporating human-in-the-loop feedback, leveraging a well-trained reward model aligned with human preferences. Using a d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.18204","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/2504.18204/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":"2026-07-05T10:54:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"seIBrvQNQDRpceCsmtHp3jM877MWjHyHut+LhYVPU+EiTtABwW9oq3gsnVllSE4ntde94wNUqAgzLPIc9IJyAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T13:48:18.917918Z"},"content_sha256":"3a7e21e133ce02aa6d040f5c9ab740839d1901c914fae965dde16aebfc6072a3","schema_version":"1.0","event_id":"sha256:3a7e21e133ce02aa6d040f5c9ab740839d1901c914fae965dde16aebfc6072a3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TLK4TGR4ADTRWRLLDJQHOGWBP6/bundle.json","state_url":"https://pith.science/pith/TLK4TGR4ADTRWRLLDJQHOGWBP6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TLK4TGR4ADTRWRLLDJQHOGWBP6/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":"2026-07-06T13:48:18Z","links":{"resolver":"https://pith.science/pith/TLK4TGR4ADTRWRLLDJQHOGWBP6","bundle":"https://pith.science/pith/TLK4TGR4ADTRWRLLDJQHOGWBP6/bundle.json","state":"https://pith.science/pith/TLK4TGR4ADTRWRLLDJQHOGWBP6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TLK4TGR4ADTRWRLLDJQHOGWBP6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TLK4TGR4ADTRWRLLDJQHOGWBP6","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":"2c34e2a70d4b89641499d5ed29ca817e4b4d209b512f7431db8c68db9bcddb29","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-25T09:35:02Z","title_canon_sha256":"114343302d681a6ed9bdc1f2fe4bccfee555a6d4da62c44943dcab936f381434"},"schema_version":"1.0","source":{"id":"2504.18204","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.18204","created_at":"2026-07-05T10:54:03Z"},{"alias_kind":"arxiv_version","alias_value":"2504.18204v1","created_at":"2026-07-05T10:54:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.18204","created_at":"2026-07-05T10:54:03Z"},{"alias_kind":"pith_short_12","alias_value":"TLK4TGR4ADTR","created_at":"2026-07-05T10:54:03Z"},{"alias_kind":"pith_short_16","alias_value":"TLK4TGR4ADTRWRLL","created_at":"2026-07-05T10:54:03Z"},{"alias_kind":"pith_short_8","alias_value":"TLK4TGR4","created_at":"2026-07-05T10:54:03Z"}],"graph_snapshots":[{"event_id":"sha256:3a7e21e133ce02aa6d040f5c9ab740839d1901c914fae965dde16aebfc6072a3","target":"graph","created_at":"2026-07-05T10:54:03Z","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/2504.18204/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generative AI has significantly changed industries by enabling text-driven image generation, yet challenges remain in achieving high-resolution outputs that align with fine-grained user preferences. Consequently, multi-round interactions are necessary to ensure the generated images meet expectations. Previous methods enhanced prompts via reward feedback but did not optimize over a multi-round dialogue dataset. In this work, we present a Visual Co-Adaptation (VCA) framework incorporating human-in-the-loop feedback, leveraging a well-trained reward model aligned with human preferences. Using a d","authors_text":"Hongyang He, Jianhui Wang, Jiaqi Chen, Keqin Li, Kun Li, Miao Zhang, Ruoyu Wang, Sida Li, Tianyu Shi, Wenxin Zhang, Xinyuan Song, Xueqian Wang, Yangfan He","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-25T09:35:02Z","title":"Optimizing Multi-Round Enhanced Training in Diffusion Models for Improved Preference Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.18204","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:d26d5b9a5c8fef1836a6791c7f2b33ba4f386280309b4d11d58844392e2fcbf7","target":"record","created_at":"2026-07-05T10:54:03Z","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":"2c34e2a70d4b89641499d5ed29ca817e4b4d209b512f7431db8c68db9bcddb29","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-25T09:35:02Z","title_canon_sha256":"114343302d681a6ed9bdc1f2fe4bccfee555a6d4da62c44943dcab936f381434"},"schema_version":"1.0","source":{"id":"2504.18204","kind":"arxiv","version":1}},"canonical_sha256":"9ad5c99a3c00e71b456b1a60771ac17f9de5222d285baf19dc6cc6d09dd06fe8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9ad5c99a3c00e71b456b1a60771ac17f9de5222d285baf19dc6cc6d09dd06fe8","first_computed_at":"2026-07-05T10:54:03.678059Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:54:03.678059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"byEPMgvad59BDn356vz3AhabGYPS00R3p71QwaL0P2rOnw0DDGErHoQ60R7nvUk68loEuLHg3w1Mc4N32f2PAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:54:03.678525Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.18204","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d26d5b9a5c8fef1836a6791c7f2b33ba4f386280309b4d11d58844392e2fcbf7","sha256:3a7e21e133ce02aa6d040f5c9ab740839d1901c914fae965dde16aebfc6072a3"],"state_sha256":"aaa2c0d4f8f279867184675f84f2d886e3827fe238b337d29281d00c482037eb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VJFPIXoaneqYthdkCbgf8whhc6FbDyYlnMThqQmLb9Pf1452gFnCSlnfxFyNDbvUmeBLTisrFM9TX7bw1aDPAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T13:48:18.919895Z","bundle_sha256":"342742c7f4dc208efe54d42e79d7ea761bdcb0272ed07bb802f4ca293a3b70d4"}}