{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VJ46N2ZCILWXAENPNAG6V74DII","short_pith_number":"pith:VJ46N2ZC","schema_version":"1.0","canonical_sha256":"aa79e6eb2242ed7011af680deaff834224f5b105429daf490277954b1c084660","source":{"kind":"arxiv","id":"2603.09551","version":2},"attestation_state":"computed","paper":{"title":"GeoSolver: Scaling Test-Time Reasoning in Remote Sensing with Fine-Grained Process Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Yang, Haoran Liu, Lang Sun, Ronghao Fu, Xueyan Liu, Zhuoran Duan","submitted_at":"2026-03-10T11:59:05Z","abstract_excerpt":"While Vision-Language Models (VLMs) have significantly advanced remote sensing interpretation, enabling them to perform complex, step-by-step reasoning remains highly challenging. Recent efforts to introduce Chain-of-Thought (CoT) reasoning to this domain have shown promise, yet ensuring the visual faithfulness of these intermediate steps remains a critical bottleneck. To address this, we introduce GeoSolver, a novel framework that transitions remote sensing reasoning toward verifiable, process-supervised reinforcement learning. We first construct Geo-PRM-2M, a large-scale, token-level process"},"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":"2603.09551","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-03-10T11:59:05Z","cross_cats_sorted":[],"title_canon_sha256":"19fb396ae04d7ef6efe804835ed972e20fac39e4f4e283120e7bf9016da2d0ad","abstract_canon_sha256":"4f2777e4e51c480dd5b133f3367943ff8173c81a427db3d89da3e5df57c1b507"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:05:45.984618Z","signature_b64":"ZLhR5G1mp1iTVha9gOtPkBN04JhZ6nOSznlrnEldd/7zqnHcsdCo3ES5Vg1y23VsRkMs1v6P9ARWUqcZSEUPBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa79e6eb2242ed7011af680deaff834224f5b105429daf490277954b1c084660","last_reissued_at":"2026-05-27T01:05:45.983718Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:05:45.983718Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GeoSolver: Scaling Test-Time Reasoning in Remote Sensing with Fine-Grained Process Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Yang, Haoran Liu, Lang Sun, Ronghao Fu, Xueyan Liu, Zhuoran Duan","submitted_at":"2026-03-10T11:59:05Z","abstract_excerpt":"While Vision-Language Models (VLMs) have significantly advanced remote sensing interpretation, enabling them to perform complex, step-by-step reasoning remains highly challenging. Recent efforts to introduce Chain-of-Thought (CoT) reasoning to this domain have shown promise, yet ensuring the visual faithfulness of these intermediate steps remains a critical bottleneck. To address this, we introduce GeoSolver, a novel framework that transitions remote sensing reasoning toward verifiable, process-supervised reinforcement learning. We first construct Geo-PRM-2M, a large-scale, token-level process"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.09551","kind":"arxiv","version":2},"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/2603.09551/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":"2603.09551","created_at":"2026-05-27T01:05:45.983827+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.09551v2","created_at":"2026-05-27T01:05:45.983827+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.09551","created_at":"2026-05-27T01:05:45.983827+00:00"},{"alias_kind":"pith_short_12","alias_value":"VJ46N2ZCILWX","created_at":"2026-05-27T01:05:45.983827+00:00"},{"alias_kind":"pith_short_16","alias_value":"VJ46N2ZCILWXAENP","created_at":"2026-05-27T01:05:45.983827+00:00"},{"alias_kind":"pith_short_8","alias_value":"VJ46N2ZC","created_at":"2026-05-27T01:05:45.983827+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VJ46N2ZCILWXAENPNAG6V74DII","json":"https://pith.science/pith/VJ46N2ZCILWXAENPNAG6V74DII.json","graph_json":"https://pith.science/api/pith-number/VJ46N2ZCILWXAENPNAG6V74DII/graph.json","events_json":"https://pith.science/api/pith-number/VJ46N2ZCILWXAENPNAG6V74DII/events.json","paper":"https://pith.science/paper/VJ46N2ZC"},"agent_actions":{"view_html":"https://pith.science/pith/VJ46N2ZCILWXAENPNAG6V74DII","download_json":"https://pith.science/pith/VJ46N2ZCILWXAENPNAG6V74DII.json","view_paper":"https://pith.science/paper/VJ46N2ZC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.09551&json=true","fetch_graph":"https://pith.science/api/pith-number/VJ46N2ZCILWXAENPNAG6V74DII/graph.json","fetch_events":"https://pith.science/api/pith-number/VJ46N2ZCILWXAENPNAG6V74DII/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VJ46N2ZCILWXAENPNAG6V74DII/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VJ46N2ZCILWXAENPNAG6V74DII/action/storage_attestation","attest_author":"https://pith.science/pith/VJ46N2ZCILWXAENPNAG6V74DII/action/author_attestation","sign_citation":"https://pith.science/pith/VJ46N2ZCILWXAENPNAG6V74DII/action/citation_signature","submit_replication":"https://pith.science/pith/VJ46N2ZCILWXAENPNAG6V74DII/action/replication_record"}},"created_at":"2026-05-27T01:05:45.983827+00:00","updated_at":"2026-05-27T01:05:45.983827+00:00"}