{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TVEIOR7XAJ4QSVDADQ7SH3ES7A","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":"eaaddef3a05b3b76dfb5d8e3623b05129030c1ee3ca5a071a3c6a90757e51beb","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-11T08:48:06Z","title_canon_sha256":"d6c8b9629d1dcba160e191f5558031c4b1c1c41ddd611d94b34b1176dc6ae6d1"},"schema_version":"1.0","source":{"id":"2407.08303","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.08303","created_at":"2026-07-05T09:39:24Z"},{"alias_kind":"arxiv_version","alias_value":"2407.08303v2","created_at":"2026-07-05T09:39:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.08303","created_at":"2026-07-05T09:39:24Z"},{"alias_kind":"pith_short_12","alias_value":"TVEIOR7XAJ4Q","created_at":"2026-07-05T09:39:24Z"},{"alias_kind":"pith_short_16","alias_value":"TVEIOR7XAJ4QSVDA","created_at":"2026-07-05T09:39:24Z"},{"alias_kind":"pith_short_8","alias_value":"TVEIOR7X","created_at":"2026-07-05T09:39:24Z"}],"graph_snapshots":[{"event_id":"sha256:de0ea3b911b998d310bf4b6e1e8d4439a7e30c2e5ad496d7f9ef177e5c9a3f21","target":"graph","created_at":"2026-07-05T09:39:24Z","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/2407.08303/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing Multimodal Large Language Models (MLLMs) increasingly emphasize complex understanding of various visual elements, including multiple objects, text information, and spatial relations. Their development for comprehensive visual perception hinges on the availability of high-quality image-text datasets that offer diverse visual elements and throughout image descriptions. However, the scarcity of such hyper-detailed datasets currently hinders progress within the MLLM community. The bottleneck stems from the limited perceptual capabilities of current caption engines, which fall short in pro","authors_text":"Fan Zhang, Haiwen Diao, Ling-Yu Duan, Xiaotong Li, Xinlong Wang, Yueze Wang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-11T08:48:06Z","title":"DenseFusion-1M: Merging Vision Experts for Comprehensive Multimodal Perception"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.08303","kind":"arxiv","version":2},"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":"sha256:8cb51bc896a34e1b9f440a8cffa8eecab7dd385eea816ae82f13e463ec2375eb","target":"record","created_at":"2026-07-05T09:39:24Z","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":"eaaddef3a05b3b76dfb5d8e3623b05129030c1ee3ca5a071a3c6a90757e51beb","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-11T08:48:06Z","title_canon_sha256":"d6c8b9629d1dcba160e191f5558031c4b1c1c41ddd611d94b34b1176dc6ae6d1"},"schema_version":"1.0","source":{"id":"2407.08303","kind":"arxiv","version":2}},"canonical_sha256":"9d488747f702790954601c3f23ec92f83fd9788d8689bab462bb0589f3160bea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9d488747f702790954601c3f23ec92f83fd9788d8689bab462bb0589f3160bea","first_computed_at":"2026-07-05T09:39:24.931636Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:39:24.931636Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"q+DsMN/OHF4RTRgIkTG8uWKkiNu+XMZ9kLKnjuqX8Lsbhxh+2G9v/Isc6s5RjUaMnetzP6nWROoCilawfqVGAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:39:24.932111Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.08303","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8cb51bc896a34e1b9f440a8cffa8eecab7dd385eea816ae82f13e463ec2375eb","sha256:de0ea3b911b998d310bf4b6e1e8d4439a7e30c2e5ad496d7f9ef177e5c9a3f21"],"state_sha256":"1c0eb29e7c4d5c095c6893c672147aaf13285e3d441b81248495464aecdbe9b0"}