{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HZFBGQRIDYEGUB4MXQHLZXBPWL","short_pith_number":"pith:HZFBGQRI","schema_version":"1.0","canonical_sha256":"3e4a1342281e086a078cbc0ebcdc2fb2f270bf1a8820531dea6152530a0b42a9","source":{"kind":"arxiv","id":"2501.14905","version":1},"attestation_state":"computed","paper":{"title":"Measuring and Mitigating Hallucinations in Vision-Language Dataset Generation for Remote Sensing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"J. Taylor Perron, Kerri Cahoy, Madeline Anderson, Miriam Cha, Nathaniel Maidel, William T. Freeman","submitted_at":"2025-01-24T20:13:29Z","abstract_excerpt":"Vision language models have achieved impressive results across various fields. However, adoption in remote sensing remains limited, largely due to the scarcity of paired image-text data. To bridge this gap, synthetic caption generation has gained interest, traditionally relying on rule-based methods that use metadata or bounding boxes. While these approaches provide some description, they often lack the depth needed to capture complex wide-area scenes. Large language models (LLMs) offer a promising alternative for generating more descriptive captions, yet they can produce generic outputs and a"},"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":"2501.14905","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-24T20:13:29Z","cross_cats_sorted":[],"title_canon_sha256":"4ef10ba85869e05e12114881aca3ad5bddd71655d42f9da73258b7a4ecdcbc45","abstract_canon_sha256":"f637c556acc9d3b8b5844c027a8a3d3091c757e7163351f126a99135981da709"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:20.533111Z","signature_b64":"qdYTuR8PdkNsvYv2m9uJSbpTOoHEN8y/WwIRMnfVkU1s/mNwq6XcU+JaioZ/od7g3Qvy3QfTDgJOVqIbx3iUDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e4a1342281e086a078cbc0ebcdc2fb2f270bf1a8820531dea6152530a0b42a9","last_reissued_at":"2026-07-05T10:05:20.532697Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:20.532697Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Measuring and Mitigating Hallucinations in Vision-Language Dataset Generation for Remote Sensing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"J. Taylor Perron, Kerri Cahoy, Madeline Anderson, Miriam Cha, Nathaniel Maidel, William T. Freeman","submitted_at":"2025-01-24T20:13:29Z","abstract_excerpt":"Vision language models have achieved impressive results across various fields. However, adoption in remote sensing remains limited, largely due to the scarcity of paired image-text data. To bridge this gap, synthetic caption generation has gained interest, traditionally relying on rule-based methods that use metadata or bounding boxes. While these approaches provide some description, they often lack the depth needed to capture complex wide-area scenes. Large language models (LLMs) offer a promising alternative for generating more descriptive captions, yet they can produce generic outputs and a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.14905","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/2501.14905/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":"2501.14905","created_at":"2026-07-05T10:05:20.532756+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.14905v1","created_at":"2026-07-05T10:05:20.532756+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.14905","created_at":"2026-07-05T10:05:20.532756+00:00"},{"alias_kind":"pith_short_12","alias_value":"HZFBGQRIDYEG","created_at":"2026-07-05T10:05:20.532756+00:00"},{"alias_kind":"pith_short_16","alias_value":"HZFBGQRIDYEGUB4M","created_at":"2026-07-05T10:05:20.532756+00:00"},{"alias_kind":"pith_short_8","alias_value":"HZFBGQRI","created_at":"2026-07-05T10:05:20.532756+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/HZFBGQRIDYEGUB4MXQHLZXBPWL","json":"https://pith.science/pith/HZFBGQRIDYEGUB4MXQHLZXBPWL.json","graph_json":"https://pith.science/api/pith-number/HZFBGQRIDYEGUB4MXQHLZXBPWL/graph.json","events_json":"https://pith.science/api/pith-number/HZFBGQRIDYEGUB4MXQHLZXBPWL/events.json","paper":"https://pith.science/paper/HZFBGQRI"},"agent_actions":{"view_html":"https://pith.science/pith/HZFBGQRIDYEGUB4MXQHLZXBPWL","download_json":"https://pith.science/pith/HZFBGQRIDYEGUB4MXQHLZXBPWL.json","view_paper":"https://pith.science/paper/HZFBGQRI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.14905&json=true","fetch_graph":"https://pith.science/api/pith-number/HZFBGQRIDYEGUB4MXQHLZXBPWL/graph.json","fetch_events":"https://pith.science/api/pith-number/HZFBGQRIDYEGUB4MXQHLZXBPWL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HZFBGQRIDYEGUB4MXQHLZXBPWL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HZFBGQRIDYEGUB4MXQHLZXBPWL/action/storage_attestation","attest_author":"https://pith.science/pith/HZFBGQRIDYEGUB4MXQHLZXBPWL/action/author_attestation","sign_citation":"https://pith.science/pith/HZFBGQRIDYEGUB4MXQHLZXBPWL/action/citation_signature","submit_replication":"https://pith.science/pith/HZFBGQRIDYEGUB4MXQHLZXBPWL/action/replication_record"}},"created_at":"2026-07-05T10:05:20.532756+00:00","updated_at":"2026-07-05T10:05:20.532756+00:00"}