{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MEZHXZTXL56ZSF3H6K5B7QA4XL","short_pith_number":"pith:MEZHXZTX","schema_version":"1.0","canonical_sha256":"61327be6775f7d991767f2ba1fc01cbac3d6dda2ff991cc8397915cc394688ba","source":{"kind":"arxiv","id":"2508.13086","version":1},"attestation_state":"computed","paper":{"title":"Checkmate: interpretable and explainable RSVQA is the endgame","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Christel Tartini Chappuis, Devis Tuia, Flora Weissgerber, Lucrezia Tosato, Sylvain Lobry, Syrielle Montariol","submitted_at":"2025-08-18T16:59:43Z","abstract_excerpt":"Remote Sensing Visual Question Answering (RSVQA) presents unique challenges in ensuring that model decisions are both understandable and grounded in visual content. Current models often suffer from a lack of interpretability and explainability, as well as from biases in dataset distributions that lead to shortcut learning. In this work, we tackle these issues by introducing a novel RSVQA dataset, Chessboard, designed to minimize biases through 3'123'253 questions and a balanced answer distribution. Each answer is linked to one or more cells within the image, enabling fine-grained visual reason"},"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":"2508.13086","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-18T16:59:43Z","cross_cats_sorted":[],"title_canon_sha256":"7bd4e10ee5e7874a625ae0e767147e7a112c5ea9422d86a5ed4312c466064ce9","abstract_canon_sha256":"da56f70b1a747b8d67d0491ca2a83ed8bcb03f488e0c12efc434fe188ea6729c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:55:32.175422Z","signature_b64":"9fJcX3A5tKlPHWNRKdw7LAFKlf4pvcmzIWOVwkzbCdc4qSw0vLppHSPUeeMV+cbrs0AigSESi3i6Si7JEKIRCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"61327be6775f7d991767f2ba1fc01cbac3d6dda2ff991cc8397915cc394688ba","last_reissued_at":"2026-07-05T11:55:32.174930Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:55:32.174930Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Checkmate: interpretable and explainable RSVQA is the endgame","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Christel Tartini Chappuis, Devis Tuia, Flora Weissgerber, Lucrezia Tosato, Sylvain Lobry, Syrielle Montariol","submitted_at":"2025-08-18T16:59:43Z","abstract_excerpt":"Remote Sensing Visual Question Answering (RSVQA) presents unique challenges in ensuring that model decisions are both understandable and grounded in visual content. Current models often suffer from a lack of interpretability and explainability, as well as from biases in dataset distributions that lead to shortcut learning. In this work, we tackle these issues by introducing a novel RSVQA dataset, Chessboard, designed to minimize biases through 3'123'253 questions and a balanced answer distribution. Each answer is linked to one or more cells within the image, enabling fine-grained visual reason"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.13086","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/2508.13086/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":"2508.13086","created_at":"2026-07-05T11:55:32.174989+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.13086v1","created_at":"2026-07-05T11:55:32.174989+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.13086","created_at":"2026-07-05T11:55:32.174989+00:00"},{"alias_kind":"pith_short_12","alias_value":"MEZHXZTXL56Z","created_at":"2026-07-05T11:55:32.174989+00:00"},{"alias_kind":"pith_short_16","alias_value":"MEZHXZTXL56ZSF3H","created_at":"2026-07-05T11:55:32.174989+00:00"},{"alias_kind":"pith_short_8","alias_value":"MEZHXZTX","created_at":"2026-07-05T11:55:32.174989+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.03189","citing_title":"Sentinel2Cap: A Human-Annotated Benchmark Dataset for Multimodal Remote Sensing Image Captioning","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MEZHXZTXL56ZSF3H6K5B7QA4XL","json":"https://pith.science/pith/MEZHXZTXL56ZSF3H6K5B7QA4XL.json","graph_json":"https://pith.science/api/pith-number/MEZHXZTXL56ZSF3H6K5B7QA4XL/graph.json","events_json":"https://pith.science/api/pith-number/MEZHXZTXL56ZSF3H6K5B7QA4XL/events.json","paper":"https://pith.science/paper/MEZHXZTX"},"agent_actions":{"view_html":"https://pith.science/pith/MEZHXZTXL56ZSF3H6K5B7QA4XL","download_json":"https://pith.science/pith/MEZHXZTXL56ZSF3H6K5B7QA4XL.json","view_paper":"https://pith.science/paper/MEZHXZTX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.13086&json=true","fetch_graph":"https://pith.science/api/pith-number/MEZHXZTXL56ZSF3H6K5B7QA4XL/graph.json","fetch_events":"https://pith.science/api/pith-number/MEZHXZTXL56ZSF3H6K5B7QA4XL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MEZHXZTXL56ZSF3H6K5B7QA4XL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MEZHXZTXL56ZSF3H6K5B7QA4XL/action/storage_attestation","attest_author":"https://pith.science/pith/MEZHXZTXL56ZSF3H6K5B7QA4XL/action/author_attestation","sign_citation":"https://pith.science/pith/MEZHXZTXL56ZSF3H6K5B7QA4XL/action/citation_signature","submit_replication":"https://pith.science/pith/MEZHXZTXL56ZSF3H6K5B7QA4XL/action/replication_record"}},"created_at":"2026-07-05T11:55:32.174989+00:00","updated_at":"2026-07-05T11:55:32.174989+00:00"}