{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:66ZBWGSAZNWNOG7K3IYNBIIHF7","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":"9107c358b30541727fcc6adff8c7c3f755b0c01dfa522bc934431bc5fa819af5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-03-30T17:59:56Z","title_canon_sha256":"57a41d644a8eb37996bb72f6f93a897936dc8ae53e3ae4cee6340580baacf3f5"},"schema_version":"1.0","source":{"id":"2603.28767","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.28767","created_at":"2026-05-25T02:02:14Z"},{"alias_kind":"arxiv_version","alias_value":"2603.28767v3","created_at":"2026-05-25T02:02:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.28767","created_at":"2026-05-25T02:02:14Z"},{"alias_kind":"pith_short_12","alias_value":"66ZBWGSAZNWN","created_at":"2026-05-25T02:02:14Z"},{"alias_kind":"pith_short_16","alias_value":"66ZBWGSAZNWNOG7K","created_at":"2026-05-25T02:02:14Z"},{"alias_kind":"pith_short_8","alias_value":"66ZBWGSA","created_at":"2026-05-25T02:02:14Z"}],"graph_snapshots":[{"event_id":"sha256:bb67c9ddaf339cc80382ddcc3d03682df8433cbbde9da9908df3ae52c3b46095","target":"graph","created_at":"2026-05-25T02:02:14Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Experiments show that Gen-Searcher brings substantial gains, improving Qwen-Image by around 16 points on KnowGen and 15 points on WISE."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That multi-hop search reliably returns accurate, relevant textual knowledge and reference images that can be directly used for grounded generation without introducing new errors or noise."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Gen-Searcher is the first search-augmented image generation agent trained with SFT followed by agentic RL using dual text and image rewards on custom datasets and the KnowGen benchmark."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Gen-Searcher trains image generators to run multi-hop searches for external knowledge and reference images before synthesis."}],"snapshot_sha256":"34783ca077761ecebae9fb5d17eb4681af2327799dc2dd9d9ef36732712179e5"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2603.28767/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent image generation models have shown strong capabilities in generating high-fidelity and photorealistic images. However, they are fundamentally constrained by frozen internal knowledge, thus often failing on real-world scenarios that are knowledge-intensive or require up-to-date information. In this paper, we present Gen-Searcher, as the first attempt to train a search-augmented image generation agent, which performs multi-hop reasoning and search to collect the textual knowledge and reference images needed for grounded generation. To achieve this, we construct a tailored data pipeline an","authors_text":"Chenyang Wang, Dian Zheng, Hongyu Li, Kaituo Feng, Kaixuan Fan, Manyuan Zhang, Shuang Chen, Xiangyu Yue, Yilei Jiang, Yunlong Lin","cross_cats":[],"headline":"Gen-Searcher trains image generators to run multi-hop searches for external knowledge and reference images before synthesis.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-03-30T17:59:56Z","title":"Gen-Searcher: Reinforcing Agentic Search for Image Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.28767","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-14T21:14:52.265561Z","id":"7236a993-1409-4316-968b-65a87751c57b","model_set":{"reader":"grok-4.3"},"one_line_summary":"Gen-Searcher is the first search-augmented image generation agent trained with SFT followed by agentic RL using dual text and image rewards on custom datasets and the KnowGen benchmark.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Gen-Searcher trains image generators to run multi-hop searches for external knowledge and reference images before synthesis.","strongest_claim":"Experiments show that Gen-Searcher brings substantial gains, improving Qwen-Image by around 16 points on KnowGen and 15 points on WISE.","weakest_assumption":"That multi-hop search reliably returns accurate, relevant textual knowledge and reference images that can be directly used for grounded generation without introducing new errors or noise."}},"verdict_id":"7236a993-1409-4316-968b-65a87751c57b"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e945022a7abc1a43c47d07b3929b9c763a536e0b80a7605eea2ad1d4a71f646e","target":"record","created_at":"2026-05-25T02:02:14Z","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":"9107c358b30541727fcc6adff8c7c3f755b0c01dfa522bc934431bc5fa819af5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-03-30T17:59:56Z","title_canon_sha256":"57a41d644a8eb37996bb72f6f93a897936dc8ae53e3ae4cee6340580baacf3f5"},"schema_version":"1.0","source":{"id":"2603.28767","kind":"arxiv","version":3}},"canonical_sha256":"f7b21b1a40cb6cd71beada30d0a1072fdf468fea233e6f1494aa9420c4d828c1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f7b21b1a40cb6cd71beada30d0a1072fdf468fea233e6f1494aa9420c4d828c1","first_computed_at":"2026-05-25T02:02:14.798740Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-25T02:02:14.798740Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WU/h7fbcQjoVC8Sl0O0oC7HgM9Y/PJYBLmkKxVtr4MpLxpTm+8SvVEXIqjFP46IsfdAs8zk8J45T6NhHXtQ+Dw==","signature_status":"signed_v1","signed_at":"2026-05-25T02:02:14.799402Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.28767","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e945022a7abc1a43c47d07b3929b9c763a536e0b80a7605eea2ad1d4a71f646e","sha256:bb67c9ddaf339cc80382ddcc3d03682df8433cbbde9da9908df3ae52c3b46095"],"state_sha256":"e0f2368b30482bd736cd86d1ad29e6c9b56a19da0b72699b9fa1afd95eb5fd8a"}