{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:2NJ4TGRPZFGF56BVIPUHRD5APF","short_pith_number":"pith:2NJ4TGRP","canonical_record":{"source":{"id":"2602.07045","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-02-04T08:21:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f31cd9106906dee5d06b7a26a26f820d950b1cc549e363b88fcf50dbcd2bef30","abstract_canon_sha256":"4980d0eb0ac90c35cfb83fa6eb5675cfe7c9c0066b7963d4b84648123d1c876c"},"schema_version":"1.0"},"canonical_sha256":"d353c99a2fc94c5ef83543e8788fa07954fab7d6bd20d4b69f26e2ed32a542a4","source":{"kind":"arxiv","id":"2602.07045","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.07045","created_at":"2026-05-17T23:39:16Z"},{"alias_kind":"arxiv_version","alias_value":"2602.07045v2","created_at":"2026-05-17T23:39:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.07045","created_at":"2026-05-17T23:39:16Z"},{"alias_kind":"pith_short_12","alias_value":"2NJ4TGRPZFGF","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"2NJ4TGRPZFGF56BV","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"2NJ4TGRP","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:2NJ4TGRPZFGF56BVIPUHRD5APF","target":"record","payload":{"canonical_record":{"source":{"id":"2602.07045","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-02-04T08:21:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f31cd9106906dee5d06b7a26a26f820d950b1cc549e363b88fcf50dbcd2bef30","abstract_canon_sha256":"4980d0eb0ac90c35cfb83fa6eb5675cfe7c9c0066b7963d4b84648123d1c876c"},"schema_version":"1.0"},"canonical_sha256":"d353c99a2fc94c5ef83543e8788fa07954fab7d6bd20d4b69f26e2ed32a542a4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:16.276350Z","signature_b64":"zb2e+vci5vV6NXXiKJnVt0kiItMCf+e49CyDWPAHnIcPBg3AGZwI/XyWKrwIJrXl3xMBksr/xzV2+bwUyv1cBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d353c99a2fc94c5ef83543e8788fa07954fab7d6bd20d4b69f26e2ed32a542a4","last_reissued_at":"2026-05-17T23:39:16.275681Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:16.275681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2602.07045","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KUHj6OuHcd5EsUXL0bQRSyCd+dNVp8ytpwQBCNQAYSASNjZDXsi+lQRUEEZJmGJQUJ9eedEUq7460ZJygqm2Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T02:28:14.060041Z"},"content_sha256":"1d3360baf392e067d8c097a664d76fab27a57ce684b6a93220b818326c12e8fe","schema_version":"1.0","event_id":"sha256:1d3360baf392e067d8c097a664d76fab27a57ce684b6a93220b818326c12e8fe"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:2NJ4TGRPZFGF56BVIPUHRD5APF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VLRS-Bench: A Vision-Language Reasoning Benchmark for Remote Sensing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"VLRS-Bench is the first benchmark built exclusively for complex vision-language reasoning in remote sensing.","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bo Du, Di Wang, Haonan Guo, Jing Zhang, Zhiming Luo","submitted_at":"2026-02-04T08:21:33Z","abstract_excerpt":"Recent advancements in Multimodal Large Language Models (MLLMs) have enabled complex reasoning. However, existing remote sensing (RS) benchmarks remain heavily biased toward perception tasks, such as object recognition and scene classification. This limitation hinders the development of MLLMs for cognitively demanding RS applications. To address this, we propose a Vision Language ReaSoning Benchmark (VLRS-Bench), which is the first benchmark exclusively dedicated to complex RS reasoning. Structured across the three core dimensions of Cognition, Decision, and Prediction, VLRS-Bench comprises 2,"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"VLRS-Bench is the first benchmark exclusively dedicated to complex RS reasoning.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The specialized pipeline that integrates RS-specific priors and expert knowledge produces questions with genuine geospatial realism and reasoning complexity.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"VLRS-Bench is the first benchmark dedicated to complex vision-language reasoning in remote sensing, with 2000 QA pairs across 14 tasks in cognition, decision, and prediction dimensions.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"VLRS-Bench is the first benchmark built exclusively for complex vision-language reasoning in remote sensing.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"05c118101ad1609c7707839e3a8d879464da4d4c0c63b403076c900b25796f9a"},"source":{"id":"2602.07045","kind":"arxiv","version":2},"verdict":{"id":"fb03f4f5-3ef0-4321-bfe0-469d96f06f51","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T08:03:33.151871Z","strongest_claim":"VLRS-Bench is the first benchmark exclusively dedicated to complex RS reasoning.","one_line_summary":"VLRS-Bench is the first benchmark dedicated to complex vision-language reasoning in remote sensing, with 2000 QA pairs across 14 tasks in cognition, decision, and prediction dimensions.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The specialized pipeline that integrates RS-specific priors and expert knowledge produces questions with genuine geospatial realism and reasoning complexity.","pith_extraction_headline":"VLRS-Bench is the first benchmark built exclusively for complex vision-language reasoning in remote sensing."},"references":{"count":66,"sample":[{"doi":"","year":2025,"title":"Choice: Benchmarking the remote sensing capabilities of large vision-language models","work_id":"5368693c-f5d0-4484-bf91-3cc6cbd81b36","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Qwen2.5-VL Technical Report","work_id":"69dffacb-bfe8-442d-be86-48624c60426f","ref_index":2,"cited_arxiv_id":"2502.13923","is_internal_anchor":true},{"doi":"","year":1912,"title":"Dota 2 with Large Scale Deep Reinforcement Learning","work_id":"b047dc18-e9a3-4d11-8ff6-cd59d41a6357","ref_index":3,"cited_arxiv_id":"1912.06680","is_internal_anchor":true},{"doi":"","year":2024,"title":"Towards injecting medical vi- sual knowledge into multimodal llms at scale","work_id":"4891d5b6-63ba-4ad7-80db-b16538e41835","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Are We on the Right Way for Evaluating Large Vision-Language Models?","work_id":"0d0b977c-a42e-49b1-869e-b7360dca5282","ref_index":5,"cited_arxiv_id":"2403.20330","is_internal_anchor":true}],"resolved_work":66,"snapshot_sha256":"46263ef8fd3b00375aaa9d9b3a55620783979cc5de8029f15c4db0938353a0ba","internal_anchors":9},"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"},"verdict_id":"fb03f4f5-3ef0-4321-bfe0-469d96f06f51"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qKYG4w0wi9oa5a6Vevm50ZBYLguiOLO2+f9HE2SCChVCUj8yodTO84er4DfEZmR76stYkQ+jF2Q7s/DieSwIDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T02:28:14.061032Z"},"content_sha256":"fdc12fc0faad03e4514354a6be8ad77de084bb392a771c5af025e77a3c87ff92","schema_version":"1.0","event_id":"sha256:fdc12fc0faad03e4514354a6be8ad77de084bb392a771c5af025e77a3c87ff92"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2NJ4TGRPZFGF56BVIPUHRD5APF/bundle.json","state_url":"https://pith.science/pith/2NJ4TGRPZFGF56BVIPUHRD5APF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2NJ4TGRPZFGF56BVIPUHRD5APF/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-27T02:28:14Z","links":{"resolver":"https://pith.science/pith/2NJ4TGRPZFGF56BVIPUHRD5APF","bundle":"https://pith.science/pith/2NJ4TGRPZFGF56BVIPUHRD5APF/bundle.json","state":"https://pith.science/pith/2NJ4TGRPZFGF56BVIPUHRD5APF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2NJ4TGRPZFGF56BVIPUHRD5APF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2NJ4TGRPZFGF56BVIPUHRD5APF","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":"4980d0eb0ac90c35cfb83fa6eb5675cfe7c9c0066b7963d4b84648123d1c876c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-02-04T08:21:33Z","title_canon_sha256":"f31cd9106906dee5d06b7a26a26f820d950b1cc549e363b88fcf50dbcd2bef30"},"schema_version":"1.0","source":{"id":"2602.07045","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.07045","created_at":"2026-05-17T23:39:16Z"},{"alias_kind":"arxiv_version","alias_value":"2602.07045v2","created_at":"2026-05-17T23:39:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.07045","created_at":"2026-05-17T23:39:16Z"},{"alias_kind":"pith_short_12","alias_value":"2NJ4TGRPZFGF","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"2NJ4TGRPZFGF56BV","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"2NJ4TGRP","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:fdc12fc0faad03e4514354a6be8ad77de084bb392a771c5af025e77a3c87ff92","target":"graph","created_at":"2026-05-17T23:39:16Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"VLRS-Bench is the first benchmark exclusively dedicated to complex RS reasoning."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The specialized pipeline that integrates RS-specific priors and expert knowledge produces questions with genuine geospatial realism and reasoning complexity."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"VLRS-Bench is the first benchmark dedicated to complex vision-language reasoning in remote sensing, with 2000 QA pairs across 14 tasks in cognition, decision, and prediction dimensions."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"VLRS-Bench is the first benchmark built exclusively for complex vision-language reasoning in remote sensing."}],"snapshot_sha256":"05c118101ad1609c7707839e3a8d879464da4d4c0c63b403076c900b25796f9a"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Recent advancements in Multimodal Large Language Models (MLLMs) have enabled complex reasoning. However, existing remote sensing (RS) benchmarks remain heavily biased toward perception tasks, such as object recognition and scene classification. This limitation hinders the development of MLLMs for cognitively demanding RS applications. To address this, we propose a Vision Language ReaSoning Benchmark (VLRS-Bench), which is the first benchmark exclusively dedicated to complex RS reasoning. Structured across the three core dimensions of Cognition, Decision, and Prediction, VLRS-Bench comprises 2,","authors_text":"Bo Du, Di Wang, Haonan Guo, Jing Zhang, Zhiming Luo","cross_cats":["cs.AI"],"headline":"VLRS-Bench is the first benchmark built exclusively for complex vision-language reasoning in remote sensing.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-02-04T08:21:33Z","title":"VLRS-Bench: A Vision-Language Reasoning Benchmark for Remote Sensing"},"references":{"count":66,"internal_anchors":9,"resolved_work":66,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Choice: Benchmarking the remote sensing capabilities of large vision-language models","work_id":"5368693c-f5d0-4484-bf91-3cc6cbd81b36","year":2025},{"cited_arxiv_id":"2502.13923","doi":"","is_internal_anchor":true,"ref_index":2,"title":"Qwen2.5-VL Technical Report","work_id":"69dffacb-bfe8-442d-be86-48624c60426f","year":2025},{"cited_arxiv_id":"1912.06680","doi":"","is_internal_anchor":true,"ref_index":3,"title":"Dota 2 with Large Scale Deep Reinforcement Learning","work_id":"b047dc18-e9a3-4d11-8ff6-cd59d41a6357","year":1912},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Towards injecting medical vi- sual knowledge into multimodal llms at scale","work_id":"4891d5b6-63ba-4ad7-80db-b16538e41835","year":2024},{"cited_arxiv_id":"2403.20330","doi":"","is_internal_anchor":true,"ref_index":5,"title":"Are We on the Right Way for Evaluating Large Vision-Language Models?","work_id":"0d0b977c-a42e-49b1-869e-b7360dca5282","year":null}],"snapshot_sha256":"46263ef8fd3b00375aaa9d9b3a55620783979cc5de8029f15c4db0938353a0ba"},"source":{"id":"2602.07045","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-16T08:03:33.151871Z","id":"fb03f4f5-3ef0-4321-bfe0-469d96f06f51","model_set":{"reader":"grok-4.3"},"one_line_summary":"VLRS-Bench is the first benchmark dedicated to complex vision-language reasoning in remote sensing, with 2000 QA pairs across 14 tasks in cognition, decision, and prediction dimensions.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"VLRS-Bench is the first benchmark built exclusively for complex vision-language reasoning in remote sensing.","strongest_claim":"VLRS-Bench is the first benchmark exclusively dedicated to complex RS reasoning.","weakest_assumption":"The specialized pipeline that integrates RS-specific priors and expert knowledge produces questions with genuine geospatial realism and reasoning complexity."}},"verdict_id":"fb03f4f5-3ef0-4321-bfe0-469d96f06f51"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1d3360baf392e067d8c097a664d76fab27a57ce684b6a93220b818326c12e8fe","target":"record","created_at":"2026-05-17T23:39:16Z","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":"4980d0eb0ac90c35cfb83fa6eb5675cfe7c9c0066b7963d4b84648123d1c876c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-02-04T08:21:33Z","title_canon_sha256":"f31cd9106906dee5d06b7a26a26f820d950b1cc549e363b88fcf50dbcd2bef30"},"schema_version":"1.0","source":{"id":"2602.07045","kind":"arxiv","version":2}},"canonical_sha256":"d353c99a2fc94c5ef83543e8788fa07954fab7d6bd20d4b69f26e2ed32a542a4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d353c99a2fc94c5ef83543e8788fa07954fab7d6bd20d4b69f26e2ed32a542a4","first_computed_at":"2026-05-17T23:39:16.275681Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:16.275681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zb2e+vci5vV6NXXiKJnVt0kiItMCf+e49CyDWPAHnIcPBg3AGZwI/XyWKrwIJrXl3xMBksr/xzV2+bwUyv1cBg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:16.276350Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.07045","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1d3360baf392e067d8c097a664d76fab27a57ce684b6a93220b818326c12e8fe","sha256:fdc12fc0faad03e4514354a6be8ad77de084bb392a771c5af025e77a3c87ff92"],"state_sha256":"adfb9e7d60546e698c51c09824345d6ac00658af75a17206a9f89264ad8ee5d4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nuWUQMLiDKapJm6Z0riXjimkW57wR5loKojWnjrZRUF/QGMcoz5YQw4MGT6Ri0dNxJvabW6hFqGF1nesjclACw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T02:28:14.065294Z","bundle_sha256":"2bf7e98b28f57ff29809fcc3c74df529ba3e3e44e95288a1fc4f0743c7c08a74"}}