{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KBYQH2APPLH2JMXA53JQ3B4LJP","short_pith_number":"pith:KBYQH2AP","schema_version":"1.0","canonical_sha256":"507103e80f7acfa4b2e0eed30d878b4bf8839a984c1b2b6b43ea7aca80698e3e","source":{"kind":"arxiv","id":"2607.15942","version":1},"attestation_state":"computed","paper":{"title":"More with Less: a Large Scale Remote Sensing VLM with a Simple Recipe","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Danda Pani Paudel (INSAIT, Luc Van Gool, Mario Markov, Mohammad Mahdi, Sofia University \"St. Kliment Ohridski\"), Stefan Maria Ailuro","submitted_at":"2026-07-17T13:25:44Z","abstract_excerpt":"Remote sensing vision-language models are increasingly expected to support open-ended reasoning over Earth Observation data and a variety of tasks. Most recent progress in this area has been driven by remote-sensing-specific architectural designs, often introducing new encoders, alignment modules, or task-specific fusion mechanisms. In this work, we challenge the necessity of such architectural specialization. We show that a generally capable vision-language model can achieve competitive or state-of-the-art performance at challenging remote sensing benchmarks, provided that it is trained at su"},"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":"2607.15942","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-17T13:25:44Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3efad60670b363817927390a5fbda5fca41e93ca58eddfacc3ed60fd62741417","abstract_canon_sha256":"789272f18bcd781c4a3508f9d004e3f5b4f36cb44561bddcc6d3c6e50160d855"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-20T01:19:18.796636Z","signature_b64":"Fct8MJ4hXlfW+XLWaKN1WA7bStvncrWxpP4KRAq965Pq8ctSH9Xf86kXKDoqn3KjtZIAQWbOSrnKvmvYW6LPDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"507103e80f7acfa4b2e0eed30d878b4bf8839a984c1b2b6b43ea7aca80698e3e","last_reissued_at":"2026-07-20T01:19:18.795620Z","signature_status":"signed_v1","first_computed_at":"2026-07-20T01:19:18.795620Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"More with Less: a Large Scale Remote Sensing VLM with a Simple Recipe","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Danda Pani Paudel (INSAIT, Luc Van Gool, Mario Markov, Mohammad Mahdi, Sofia University \"St. Kliment Ohridski\"), Stefan Maria Ailuro","submitted_at":"2026-07-17T13:25:44Z","abstract_excerpt":"Remote sensing vision-language models are increasingly expected to support open-ended reasoning over Earth Observation data and a variety of tasks. Most recent progress in this area has been driven by remote-sensing-specific architectural designs, often introducing new encoders, alignment modules, or task-specific fusion mechanisms. In this work, we challenge the necessity of such architectural specialization. We show that a generally capable vision-language model can achieve competitive or state-of-the-art performance at challenging remote sensing benchmarks, provided that it is trained at su"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.15942","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/2607.15942/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":"2607.15942","created_at":"2026-07-20T01:19:18.796058+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.15942v1","created_at":"2026-07-20T01:19:18.796058+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.15942","created_at":"2026-07-20T01:19:18.796058+00:00"},{"alias_kind":"pith_short_12","alias_value":"KBYQH2APPLH2","created_at":"2026-07-20T01:19:18.796058+00:00"},{"alias_kind":"pith_short_16","alias_value":"KBYQH2APPLH2JMXA","created_at":"2026-07-20T01:19:18.796058+00:00"},{"alias_kind":"pith_short_8","alias_value":"KBYQH2AP","created_at":"2026-07-20T01:19:18.796058+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/KBYQH2APPLH2JMXA53JQ3B4LJP","json":"https://pith.science/pith/KBYQH2APPLH2JMXA53JQ3B4LJP.json","graph_json":"https://pith.science/api/pith-number/KBYQH2APPLH2JMXA53JQ3B4LJP/graph.json","events_json":"https://pith.science/api/pith-number/KBYQH2APPLH2JMXA53JQ3B4LJP/events.json","paper":"https://pith.science/paper/KBYQH2AP"},"agent_actions":{"view_html":"https://pith.science/pith/KBYQH2APPLH2JMXA53JQ3B4LJP","download_json":"https://pith.science/pith/KBYQH2APPLH2JMXA53JQ3B4LJP.json","view_paper":"https://pith.science/paper/KBYQH2AP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.15942&json=true","fetch_graph":"https://pith.science/api/pith-number/KBYQH2APPLH2JMXA53JQ3B4LJP/graph.json","fetch_events":"https://pith.science/api/pith-number/KBYQH2APPLH2JMXA53JQ3B4LJP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KBYQH2APPLH2JMXA53JQ3B4LJP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KBYQH2APPLH2JMXA53JQ3B4LJP/action/storage_attestation","attest_author":"https://pith.science/pith/KBYQH2APPLH2JMXA53JQ3B4LJP/action/author_attestation","sign_citation":"https://pith.science/pith/KBYQH2APPLH2JMXA53JQ3B4LJP/action/citation_signature","submit_replication":"https://pith.science/pith/KBYQH2APPLH2JMXA53JQ3B4LJP/action/replication_record"}},"created_at":"2026-07-20T01:19:18.796058+00:00","updated_at":"2026-07-20T01:19:18.796058+00:00"}