{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RSLFPNGHFY47VK3RVHKS5NR7LD","short_pith_number":"pith:RSLFPNGH","schema_version":"1.0","canonical_sha256":"8c9657b4c72e39faab71a9d52eb63f58e0363be7679f1f848bb63da5f16c2650","source":{"kind":"arxiv","id":"2506.12776","version":1},"attestation_state":"computed","paper":{"title":"Native Visual Understanding: Resolving Resolution Dilemmas in Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bohan Zeng, Chunjiang Ge, Conghui He, Hao Liang, Hejun Dong, Junbo Niu, Ma Lu, Qiahao Zheng, Wentao Zhang, Yuanhong Zheng, Ziyang Miao","submitted_at":"2025-06-15T08:58:09Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2506.12776","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-15T08:58:09Z","cross_cats_sorted":[],"title_canon_sha256":"7bb04ac6590164e012c59888d30ed5973db4a88bd8d4d2ff8b4cd4e80c17781e","abstract_canon_sha256":"3f56cff25dfe7bbcc93d266e1c0afa20e35a5980d164bfe4783e95abea3b8bd4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:59.810337Z","signature_b64":"l8IKKconr6C9HqKjWzMyN7u0w/xMxaJRYu0u55Goo8eZnz7E92JGaKnaUdq7lQ0HZGuLvXDtflJ5RNBPPk/PBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c9657b4c72e39faab71a9d52eb63f58e0363be7679f1f848bb63da5f16c2650","last_reissued_at":"2026-07-05T11:21:59.809833Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:59.809833Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Native Visual Understanding: Resolving Resolution Dilemmas in Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bohan Zeng, Chunjiang Ge, Conghui He, Hao Liang, Hejun Dong, Junbo Niu, Ma Lu, Qiahao Zheng, Wentao Zhang, Yuanhong Zheng, Ziyang Miao","submitted_at":"2025-06-15T08:58:09Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.12776","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2506.12776/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2506.12776","created_at":"2026-07-05T11:21:59.809893+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.12776v1","created_at":"2026-07-05T11:21:59.809893+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.12776","created_at":"2026-07-05T11:21:59.809893+00:00"},{"alias_kind":"pith_short_12","alias_value":"RSLFPNGHFY47","created_at":"2026-07-05T11:21:59.809893+00:00"},{"alias_kind":"pith_short_16","alias_value":"RSLFPNGHFY47VK3R","created_at":"2026-07-05T11:21:59.809893+00:00"},{"alias_kind":"pith_short_8","alias_value":"RSLFPNGH","created_at":"2026-07-05T11:21:59.809893+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07861","citing_title":"The Last Visible Pixel: Probing Fine-Scale Perception in Vision-Language Models","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2509.22186","citing_title":"MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04771","citing_title":"MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scale","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RSLFPNGHFY47VK3RVHKS5NR7LD","json":"https://pith.science/pith/RSLFPNGHFY47VK3RVHKS5NR7LD.json","graph_json":"https://pith.science/api/pith-number/RSLFPNGHFY47VK3RVHKS5NR7LD/graph.json","events_json":"https://pith.science/api/pith-number/RSLFPNGHFY47VK3RVHKS5NR7LD/events.json","paper":"https://pith.science/paper/RSLFPNGH"},"agent_actions":{"view_html":"https://pith.science/pith/RSLFPNGHFY47VK3RVHKS5NR7LD","download_json":"https://pith.science/pith/RSLFPNGHFY47VK3RVHKS5NR7LD.json","view_paper":"https://pith.science/paper/RSLFPNGH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.12776&json=true","fetch_graph":"https://pith.science/api/pith-number/RSLFPNGHFY47VK3RVHKS5NR7LD/graph.json","fetch_events":"https://pith.science/api/pith-number/RSLFPNGHFY47VK3RVHKS5NR7LD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RSLFPNGHFY47VK3RVHKS5NR7LD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RSLFPNGHFY47VK3RVHKS5NR7LD/action/storage_attestation","attest_author":"https://pith.science/pith/RSLFPNGHFY47VK3RVHKS5NR7LD/action/author_attestation","sign_citation":"https://pith.science/pith/RSLFPNGHFY47VK3RVHKS5NR7LD/action/citation_signature","submit_replication":"https://pith.science/pith/RSLFPNGHFY47VK3RVHKS5NR7LD/action/replication_record"}},"created_at":"2026-07-05T11:21:59.809893+00:00","updated_at":"2026-07-05T11:21:59.809893+00:00"}