{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GXIOO42RDVEY2TKLQB6NU4N7FU","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":"df248a1018747915cdbc9a74afa65d4897893af1b7a0e1fb9e115111898dc603","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-08T17:23:36Z","title_canon_sha256":"955c73902c7e15182b86b365e957fc34c0b50e094fc026a40eab2dd512cd749e"},"schema_version":"1.0","source":{"id":"2506.07227","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.07227","created_at":"2026-07-05T11:18:03Z"},{"alias_kind":"arxiv_version","alias_value":"2506.07227v1","created_at":"2026-07-05T11:18:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07227","created_at":"2026-07-05T11:18:03Z"},{"alias_kind":"pith_short_12","alias_value":"GXIOO42RDVEY","created_at":"2026-07-05T11:18:03Z"},{"alias_kind":"pith_short_16","alias_value":"GXIOO42RDVEY2TKL","created_at":"2026-07-05T11:18:03Z"},{"alias_kind":"pith_short_8","alias_value":"GXIOO42R","created_at":"2026-07-05T11:18:03Z"}],"graph_snapshots":[{"event_id":"sha256:505f03dbeb755e0cfa9c30acb15aa98b842c3b73f4333efbaf0ba652c381569b","target":"graph","created_at":"2026-07-05T11:18:03Z","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/2506.07227/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal large language models (MLLMs) have achieved strong performance on vision-language tasks but still struggle with fine-grained visual differences, leading to hallucinations or missed semantic shifts. We attribute this to limitations in both training data and learning objectives. To address these issues, we propose a controlled data generation pipeline that produces minimally edited image pairs with semantically aligned captions. Using this pipeline, we construct the Micro Edit Dataset (MED), containing over 50K image-text pairs spanning 11 fine-grained edit categories, including attri","authors_text":"Binhang Yuan, Conghui He, Fupeng Sun, Jiantao Qiu, Jiayi Song, Junlin Han, Tianyi Bai, Wentao Zhang, Yuxuan Fan, Zichen Liu","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-08T17:23:36Z","title":"Hallucination at a Glance: Controlled Visual Edits and Fine-Grained Multimodal Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07227","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:fa20557b7a100d1df4cd684d51fa018d8f5d478c3b17a0a9ffeb27241cc5a20f","target":"record","created_at":"2026-07-05T11:18:03Z","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":"df248a1018747915cdbc9a74afa65d4897893af1b7a0e1fb9e115111898dc603","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-08T17:23:36Z","title_canon_sha256":"955c73902c7e15182b86b365e957fc34c0b50e094fc026a40eab2dd512cd749e"},"schema_version":"1.0","source":{"id":"2506.07227","kind":"arxiv","version":1}},"canonical_sha256":"35d0e773511d498d4d4b807cda71bf2d32564687d9f30d43476aa11bc0dc4f30","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"35d0e773511d498d4d4b807cda71bf2d32564687d9f30d43476aa11bc0dc4f30","first_computed_at":"2026-07-05T11:18:03.899919Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:18:03.899919Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LsYNySWB+yDtMjltNC4QEKSbkWXBJ0Es/mrvsMGx3+mmIaaTobt7lj18nyhSvGWxCAWRTopLXgj6fFqAwAllDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:18:03.900435Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.07227","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fa20557b7a100d1df4cd684d51fa018d8f5d478c3b17a0a9ffeb27241cc5a20f","sha256:505f03dbeb755e0cfa9c30acb15aa98b842c3b73f4333efbaf0ba652c381569b"],"state_sha256":"c0759ab9c9c9066705cead05527361ddf7d64959f22d0759ae8b96c0e3e6b480"}