{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RNXIXDIMCE3ZBQ7SZP77GMTHZN","short_pith_number":"pith:RNXIXDIM","schema_version":"1.0","canonical_sha256":"8b6e8b8d0c113790c3f2cbfff33267cb73e742f5599d54edfcb17383c9d1e07c","source":{"kind":"arxiv","id":"2503.11265","version":1},"attestation_state":"computed","paper":{"title":"DynRsl-VLM: Enhancing Autonomous Driving Perception with Dynamic Resolution Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lianlei Shan, Xiaolin Gui, Xirui Zhou","submitted_at":"2025-03-14T10:19:24Z","abstract_excerpt":"Visual Question Answering (VQA) models, which fall under the category of vision-language models, conventionally execute multiple downsampling processes on image inputs to strike a balance between computational efficiency and model performance. Although this approach aids in concentrating on salient features and diminishing computational burden, it incurs the loss of vital detailed information, a drawback that is particularly damaging in end-to-end autonomous driving scenarios. Downsampling can lead to an inadequate capture of distant or small objects such as pedestrians, road signs, or obstacl"},"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":"2503.11265","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-14T10:19:24Z","cross_cats_sorted":[],"title_canon_sha256":"5d6e5adc4e1428e69e0b9de725b0ff96be544a45315fe1012186054b7d271e58","abstract_canon_sha256":"ff9ae4d577ac9e5bf5b521c1416d389589620bb889cbe71c681fb4ada0ad4672"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:31:15.766520Z","signature_b64":"XK9LmjiRjhMJ3rzJ/WnOp5PPCA9mfTbf3deOEBx1ilm0IQJYCifk1MZxOC0S7CUrwlWrB4ZLcwc+zFG0/+dZDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b6e8b8d0c113790c3f2cbfff33267cb73e742f5599d54edfcb17383c9d1e07c","last_reissued_at":"2026-07-05T10:31:15.765993Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:31:15.765993Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DynRsl-VLM: Enhancing Autonomous Driving Perception with Dynamic Resolution Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lianlei Shan, Xiaolin Gui, Xirui Zhou","submitted_at":"2025-03-14T10:19:24Z","abstract_excerpt":"Visual Question Answering (VQA) models, which fall under the category of vision-language models, conventionally execute multiple downsampling processes on image inputs to strike a balance between computational efficiency and model performance. Although this approach aids in concentrating on salient features and diminishing computational burden, it incurs the loss of vital detailed information, a drawback that is particularly damaging in end-to-end autonomous driving scenarios. Downsampling can lead to an inadequate capture of distant or small objects such as pedestrians, road signs, or obstacl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.11265","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/2503.11265/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":"2503.11265","created_at":"2026-07-05T10:31:15.766064+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.11265v1","created_at":"2026-07-05T10:31:15.766064+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.11265","created_at":"2026-07-05T10:31:15.766064+00:00"},{"alias_kind":"pith_short_12","alias_value":"RNXIXDIMCE3Z","created_at":"2026-07-05T10:31:15.766064+00:00"},{"alias_kind":"pith_short_16","alias_value":"RNXIXDIMCE3ZBQ7S","created_at":"2026-07-05T10:31:15.766064+00:00"},{"alias_kind":"pith_short_8","alias_value":"RNXIXDIM","created_at":"2026-07-05T10:31:15.766064+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.00363","citing_title":"GDGS: 3D Gaussian Splatting Via Geometry-Guided Initialization And Dynamic Density Control","ref_index":52,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RNXIXDIMCE3ZBQ7SZP77GMTHZN","json":"https://pith.science/pith/RNXIXDIMCE3ZBQ7SZP77GMTHZN.json","graph_json":"https://pith.science/api/pith-number/RNXIXDIMCE3ZBQ7SZP77GMTHZN/graph.json","events_json":"https://pith.science/api/pith-number/RNXIXDIMCE3ZBQ7SZP77GMTHZN/events.json","paper":"https://pith.science/paper/RNXIXDIM"},"agent_actions":{"view_html":"https://pith.science/pith/RNXIXDIMCE3ZBQ7SZP77GMTHZN","download_json":"https://pith.science/pith/RNXIXDIMCE3ZBQ7SZP77GMTHZN.json","view_paper":"https://pith.science/paper/RNXIXDIM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.11265&json=true","fetch_graph":"https://pith.science/api/pith-number/RNXIXDIMCE3ZBQ7SZP77GMTHZN/graph.json","fetch_events":"https://pith.science/api/pith-number/RNXIXDIMCE3ZBQ7SZP77GMTHZN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RNXIXDIMCE3ZBQ7SZP77GMTHZN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RNXIXDIMCE3ZBQ7SZP77GMTHZN/action/storage_attestation","attest_author":"https://pith.science/pith/RNXIXDIMCE3ZBQ7SZP77GMTHZN/action/author_attestation","sign_citation":"https://pith.science/pith/RNXIXDIMCE3ZBQ7SZP77GMTHZN/action/citation_signature","submit_replication":"https://pith.science/pith/RNXIXDIMCE3ZBQ7SZP77GMTHZN/action/replication_record"}},"created_at":"2026-07-05T10:31:15.766064+00:00","updated_at":"2026-07-05T10:31:15.766064+00:00"}