{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RSLFPNGHFY47VK3RVHKS5NR7LD","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":"3f56cff25dfe7bbcc93d266e1c0afa20e35a5980d164bfe4783e95abea3b8bd4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-15T08:58:09Z","title_canon_sha256":"7bb04ac6590164e012c59888d30ed5973db4a88bd8d4d2ff8b4cd4e80c17781e"},"schema_version":"1.0","source":{"id":"2506.12776","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.12776","created_at":"2026-07-05T11:21:59Z"},{"alias_kind":"arxiv_version","alias_value":"2506.12776v1","created_at":"2026-07-05T11:21:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.12776","created_at":"2026-07-05T11:21:59Z"},{"alias_kind":"pith_short_12","alias_value":"RSLFPNGHFY47","created_at":"2026-07-05T11:21:59Z"},{"alias_kind":"pith_short_16","alias_value":"RSLFPNGHFY47VK3R","created_at":"2026-07-05T11:21:59Z"},{"alias_kind":"pith_short_8","alias_value":"RSLFPNGH","created_at":"2026-07-05T11:21:59Z"}],"graph_snapshots":[{"event_id":"sha256:c2e65b7c5fcf33c3f01ff0732a66d2d5eb1440a4952798ae5acd12ab2eca3fb1","target":"graph","created_at":"2026-07-05T11:21:59Z","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/2506.12776/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language Models (VLMs) face significant challenges when dealing with the diverse resolutions and aspect ratios of real-world images, as most existing models rely on fixed, low-resolution inputs. While recent studies have explored integrating native resolution visual encoding to improve model performance, such efforts remain fragmented and lack a systematic framework within the open-source community. Moreover, existing benchmarks fall short in evaluating VLMs under varied visual conditions, often neglecting resolution as a critical factor. To address the \"Resolution Dilemma\" stemming fro","authors_text":"Bohan Zeng, Chunjiang Ge, Conghui He, Hao Liang, Hejun Dong, Junbo Niu, Ma Lu, Qiahao Zheng, Wentao Zhang, Yuanhong Zheng, Ziyang Miao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-15T08:58:09Z","title":"Native Visual Understanding: Resolving Resolution Dilemmas in Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.12776","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:cae9a5c234a9f51b168a9ef66cb1bf4a358987903e7e028d1bfcdaa66f4a6198","target":"record","created_at":"2026-07-05T11:21:59Z","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":"3f56cff25dfe7bbcc93d266e1c0afa20e35a5980d164bfe4783e95abea3b8bd4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-15T08:58:09Z","title_canon_sha256":"7bb04ac6590164e012c59888d30ed5973db4a88bd8d4d2ff8b4cd4e80c17781e"},"schema_version":"1.0","source":{"id":"2506.12776","kind":"arxiv","version":1}},"canonical_sha256":"8c9657b4c72e39faab71a9d52eb63f58e0363be7679f1f848bb63da5f16c2650","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8c9657b4c72e39faab71a9d52eb63f58e0363be7679f1f848bb63da5f16c2650","first_computed_at":"2026-07-05T11:21:59.809833Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:21:59.809833Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"l8IKKconr6C9HqKjWzMyN7u0w/xMxaJRYu0u55Goo8eZnz7E92JGaKnaUdq7lQ0HZGuLvXDtflJ5RNBPPk/PBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:21:59.810337Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.12776","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cae9a5c234a9f51b168a9ef66cb1bf4a358987903e7e028d1bfcdaa66f4a6198","sha256:c2e65b7c5fcf33c3f01ff0732a66d2d5eb1440a4952798ae5acd12ab2eca3fb1"],"state_sha256":"e31b48ba4612af5c48f7b777e19fc8927c78831eacf97ef2403fc6f565e5c0c6"}