{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:O3P5L7RMKN7KBGL5XSVSHTZFI4","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":"d1eeaf63c430751886d0ac1a803ed635beebcedd69d4b3be4521fd8b0460ed05","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-10T07:56:23Z","title_canon_sha256":"0110453b6d89ab89bf018734ab40b96147c5b8bd763196929187d2590b33f6dc"},"schema_version":"1.0","source":{"id":"2501.05767","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.05767","created_at":"2026-07-05T10:15:48Z"},{"alias_kind":"arxiv_version","alias_value":"2501.05767v3","created_at":"2026-07-05T10:15:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.05767","created_at":"2026-07-05T10:15:48Z"},{"alias_kind":"pith_short_12","alias_value":"O3P5L7RMKN7K","created_at":"2026-07-05T10:15:48Z"},{"alias_kind":"pith_short_16","alias_value":"O3P5L7RMKN7KBGL5","created_at":"2026-07-05T10:15:48Z"},{"alias_kind":"pith_short_8","alias_value":"O3P5L7RM","created_at":"2026-07-05T10:15:48Z"}],"graph_snapshots":[{"event_id":"sha256:2fed130061d69a5b0eee9cde64fbb584ec9ee0e9cacfb80b442a99a673668050","target":"graph","created_at":"2026-07-05T10:15:48Z","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/2501.05767/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The recent advancement of Multimodal Large Language Models (MLLMs) has significantly improved their fine-grained perception of single images and general comprehension across multiple images. However, existing MLLMs still face challenges in achieving precise grounding in complex multi-image scenarios. To address this, we first explore a Chain-of-Thought (CoT) framework that integrates single-image grounding with multi-image comprehension. While partially effective, it remains unstable and struggles to capture abstract visual information due to its non-end-to-end nature. Therefore, we introduce ","authors_text":"Chao Huang, Chi Chen, Heyu Huang, Jinan Xu, Kaiyu Huang, Maosong Sun, Ruixuan Li, You Li, Yuhua Li, Zhiyuan Liu, Zonghao Guo","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-10T07:56:23Z","title":"Migician: Revealing the Magic of Free-Form Multi-Image Grounding in Multimodal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.05767","kind":"arxiv","version":3},"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:cd1a7c36b81e3171fe2bba9507160401ad38e43392585a498a63538a4d2d2966","target":"record","created_at":"2026-07-05T10:15:48Z","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":"d1eeaf63c430751886d0ac1a803ed635beebcedd69d4b3be4521fd8b0460ed05","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-10T07:56:23Z","title_canon_sha256":"0110453b6d89ab89bf018734ab40b96147c5b8bd763196929187d2590b33f6dc"},"schema_version":"1.0","source":{"id":"2501.05767","kind":"arxiv","version":3}},"canonical_sha256":"76dfd5fe2c537ea0997dbcab23cf25472e6d30d17c0cdb6a5b2931160d8918ba","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"76dfd5fe2c537ea0997dbcab23cf25472e6d30d17c0cdb6a5b2931160d8918ba","first_computed_at":"2026-07-05T10:15:48.310709Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:15:48.310709Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Add+9hlRbCm2qj745iRz6UOcu6x53VvcKhRzb/rWertliJAggGFo3GYO2hqtsP1EcSQnZDkRbdpIoS7mAmDBCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:15:48.311225Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.05767","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cd1a7c36b81e3171fe2bba9507160401ad38e43392585a498a63538a4d2d2966","sha256:2fed130061d69a5b0eee9cde64fbb584ec9ee0e9cacfb80b442a99a673668050"],"state_sha256":"f3722a89829a6a34f2c96c40893f60c8132103b2fbeb14574e3daa06850fda15"}