{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:PXQW2WNER4CP6CD7CEWSFWUAM4","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":"6390274fb39831c91e35381a2f2d4275f2c7d92c2df88d6f8c4d26fce59204bd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-09-24T09:48:28Z","title_canon_sha256":"abcc898ed88e59ca344f0da06dfbb6450df2317a2d92724e262f80c2471da65a"},"schema_version":"1.0","source":{"id":"2109.11848","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.11848","created_at":"2026-07-05T03:17:08Z"},{"alias_kind":"arxiv_version","alias_value":"2109.11848v1","created_at":"2026-07-05T03:17:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.11848","created_at":"2026-07-05T03:17:08Z"},{"alias_kind":"pith_short_12","alias_value":"PXQW2WNER4CP","created_at":"2026-07-05T03:17:08Z"},{"alias_kind":"pith_short_16","alias_value":"PXQW2WNER4CP6CD7","created_at":"2026-07-05T03:17:08Z"},{"alias_kind":"pith_short_8","alias_value":"PXQW2WNE","created_at":"2026-07-05T03:17:08Z"}],"graph_snapshots":[{"event_id":"sha256:583e270c0c77a629d429de623b989ee65b901fe5b2bed80d1f5e805b757c9826","target":"graph","created_at":"2026-07-05T03:17:08Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2109.11848/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual question answering (VQA) has recently been introduced to remote sensing to make information extraction from overhead imagery more accessible to everyone. VQA considers a question (in natural language, therefore easy to formulate) about an image and aims at providing an answer through a model based on computer vision and natural language processing methods. As such, a VQA model needs to jointly consider visual and textual features, which is frequently done through a fusion step. In this work, we study three different fusion methodologies in the context of VQA for remote sensing and analy","authors_text":"Benjamin Kellenberger, Bertrand Le Saux, Christel Chappuis, Devis Tuia, Sylvain Lobry","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-09-24T09:48:28Z","title":"How to find a good image-text embedding for remote sensing visual question answering?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.11848","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d9f3c287b6679a4980542d9df5743c700164c2db1da003ee19ac0b86ed978fe2","target":"record","created_at":"2026-07-05T03:17:08Z","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":"6390274fb39831c91e35381a2f2d4275f2c7d92c2df88d6f8c4d26fce59204bd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-09-24T09:48:28Z","title_canon_sha256":"abcc898ed88e59ca344f0da06dfbb6450df2317a2d92724e262f80c2471da65a"},"schema_version":"1.0","source":{"id":"2109.11848","kind":"arxiv","version":1}},"canonical_sha256":"7de16d59a48f04ff087f112d22da806738e1118599b4d25c21af143b1a708b66","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7de16d59a48f04ff087f112d22da806738e1118599b4d25c21af143b1a708b66","first_computed_at":"2026-07-05T03:17:08.065214Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:17:08.065214Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ESS8O5SnDYPXdMZC3SsD2+5eiw1VV4nGR06tvmoOTGpgAe8y4m/Dok3oOX/ifUgBKosCFHdO9Zn2I1EoIhvLDw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:17:08.065619Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.11848","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d9f3c287b6679a4980542d9df5743c700164c2db1da003ee19ac0b86ed978fe2","sha256:583e270c0c77a629d429de623b989ee65b901fe5b2bed80d1f5e805b757c9826"],"state_sha256":"b50393ac10b559da741bf185b312b1581c3a2caf871a343b1cda8d88475907b0"}