{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BTEE4D42NLR6F3KFQYY5KZCAV3","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":"e26b8e5e3ed592347b1874d7a10c798a7fe0d8e2d4c780e8b340a206e5e8f3e2","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-23T07:56:48Z","title_canon_sha256":"35fcc7c5cf76159be08a2586391c1fe84106b7048a2719e4c75b5359102b5a43"},"schema_version":"1.0","source":{"id":"2410.17637","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.17637","created_at":"2026-07-05T09:24:41Z"},{"alias_kind":"arxiv_version","alias_value":"2410.17637v1","created_at":"2026-07-05T09:24:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.17637","created_at":"2026-07-05T09:24:41Z"},{"alias_kind":"pith_short_12","alias_value":"BTEE4D42NLR6","created_at":"2026-07-05T09:24:41Z"},{"alias_kind":"pith_short_16","alias_value":"BTEE4D42NLR6F3KF","created_at":"2026-07-05T09:24:41Z"},{"alias_kind":"pith_short_8","alias_value":"BTEE4D42","created_at":"2026-07-05T09:24:41Z"}],"graph_snapshots":[{"event_id":"sha256:4e76f1b4058956b40d71cb1b9b2f9a065bf21bab93f538645acb24fe866899fb","target":"graph","created_at":"2026-07-05T09:24:41Z","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/2410.17637/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual preference alignment involves training Large Vision-Language Models (LVLMs) to predict human preferences between visual inputs. This is typically achieved by using labeled datasets of chosen/rejected pairs and employing optimization algorithms like direct preference optimization (DPO). Existing visual alignment methods, primarily designed for single-image scenarios, struggle to effectively handle the complexity of multi-image tasks due to the scarcity of diverse training data and the high cost of annotating chosen/rejected pairs. We present Multi-Image Augmented Direct Preference Optimi","authors_text":"Conghui He, Dahua Lin, Haodong Duan, Jiaqi Wang, Pan Zhang, Xiaoyi Dong, Yuanjun Xiong, Yuhang Cao, Yuhang Zang, Ziyu Liu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-23T07:56:48Z","title":"MIA-DPO: Multi-Image Augmented Direct Preference Optimization For Large Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.17637","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":"sha256:34d3017461db26af0832315b0ed7f3c0ced6f0c4004008b3c0701ba283500469","target":"record","created_at":"2026-07-05T09:24:41Z","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":"e26b8e5e3ed592347b1874d7a10c798a7fe0d8e2d4c780e8b340a206e5e8f3e2","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-23T07:56:48Z","title_canon_sha256":"35fcc7c5cf76159be08a2586391c1fe84106b7048a2719e4c75b5359102b5a43"},"schema_version":"1.0","source":{"id":"2410.17637","kind":"arxiv","version":1}},"canonical_sha256":"0cc84e0f9a6ae3e2ed458631d56440aed7be75312e86c452e46624dd1c07b07e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0cc84e0f9a6ae3e2ed458631d56440aed7be75312e86c452e46624dd1c07b07e","first_computed_at":"2026-07-05T09:24:41.966569Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:24:41.966569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gh/JxjHua/HBZ4Z/UDELRUhHeNvM7P9Xts4m5yDqu5tNmb3a0av/CFRuS3Y4FVh5x87YYThgsze+QkkbDSEzCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:24:41.967191Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.17637","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:34d3017461db26af0832315b0ed7f3c0ced6f0c4004008b3c0701ba283500469","sha256:4e76f1b4058956b40d71cb1b9b2f9a065bf21bab93f538645acb24fe866899fb"],"state_sha256":"319bc8895e940622607b8fb704b60a0e5ef0127eede549f50b27ca5ff51f2bf2"}