{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QPJ5G7FRYHETEK2LD73Y6S7EGM","short_pith_number":"pith:QPJ5G7FR","schema_version":"1.0","canonical_sha256":"83d3d37cb1c1c9322b4b1ff78f4be43337ce2a96a27707c424e95b5a85853452","source":{"kind":"arxiv","id":"2503.19654","version":3},"attestation_state":"computed","paper":{"title":"RGB-Th-Bench: A Dense benchmark for Visual-Thermal Understanding of Vision Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Joni Pajarinen, Mehdi Moshtaghi, Siavash H. Khajavi","submitted_at":"2025-03-25T13:43:47Z","abstract_excerpt":"We introduce RGB-Th-Bench, the first benchmark designed to evaluate the ability of Vision-Language Models (VLMs) to comprehend RGB-Thermal image pairs. While VLMs have demonstrated remarkable progress in visual reasoning and multimodal understanding, their evaluation has been predominantly limited to RGB-based benchmarks, leaving a critical gap in assessing their capabilities in infrared vision tasks. Existing visible-infrared datasets are either task-specific or lack high-quality annotations necessary for rigorous model evaluation. To address these limitations, RGB-Th-Bench provides a compreh"},"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":"2503.19654","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-25T13:43:47Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"b7f43b3c31fdf0cd4fc064764617b5765ff1e49afa63e435536163c4beecbb1f","abstract_canon_sha256":"fe272705f768eb902ad4bb71ba939ba31cce69d2534e7815db40cbfc0a41c2e7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:41:22.903651Z","signature_b64":"7YnvpSH95M4f/YJ8U/F+3hDuuVGLRZZRNMv61uKBzAslmlWcoge5n3sjiqdzfMP3fYrG54GtHgqQw9EpPXQBDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83d3d37cb1c1c9322b4b1ff78f4be43337ce2a96a27707c424e95b5a85853452","last_reissued_at":"2026-07-05T10:41:22.902903Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:41:22.902903Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RGB-Th-Bench: A Dense benchmark for Visual-Thermal Understanding of Vision Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Joni Pajarinen, Mehdi Moshtaghi, Siavash H. Khajavi","submitted_at":"2025-03-25T13:43:47Z","abstract_excerpt":"We introduce RGB-Th-Bench, the first benchmark designed to evaluate the ability of Vision-Language Models (VLMs) to comprehend RGB-Thermal image pairs. While VLMs have demonstrated remarkable progress in visual reasoning and multimodal understanding, their evaluation has been predominantly limited to RGB-based benchmarks, leaving a critical gap in assessing their capabilities in infrared vision tasks. Existing visible-infrared datasets are either task-specific or lack high-quality annotations necessary for rigorous model evaluation. To address these limitations, RGB-Th-Bench provides a compreh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.19654","kind":"arxiv","version":3},"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/2503.19654/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":"2503.19654","created_at":"2026-07-05T10:41:22.903024+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.19654v3","created_at":"2026-07-05T10:41:22.903024+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.19654","created_at":"2026-07-05T10:41:22.903024+00:00"},{"alias_kind":"pith_short_12","alias_value":"QPJ5G7FRYHET","created_at":"2026-07-05T10:41:22.903024+00:00"},{"alias_kind":"pith_short_16","alias_value":"QPJ5G7FRYHETEK2L","created_at":"2026-07-05T10:41:22.903024+00:00"},{"alias_kind":"pith_short_8","alias_value":"QPJ5G7FR","created_at":"2026-07-05T10:41:22.903024+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.21882","citing_title":"Thermo-VL: Extending Vision-Language Models to Thermal Infrared Perception","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03117","citing_title":"Revealing Physical-World Semantic Vulnerabilities: Universal Adversarial Patch for Infrared Vision-Language Models","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06124","citing_title":"Lightweight Multimodal Adaptation of Vision Language Models for Species Recognition and Habitat Context Interpretation in Drone Thermal Imagery","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QPJ5G7FRYHETEK2LD73Y6S7EGM","json":"https://pith.science/pith/QPJ5G7FRYHETEK2LD73Y6S7EGM.json","graph_json":"https://pith.science/api/pith-number/QPJ5G7FRYHETEK2LD73Y6S7EGM/graph.json","events_json":"https://pith.science/api/pith-number/QPJ5G7FRYHETEK2LD73Y6S7EGM/events.json","paper":"https://pith.science/paper/QPJ5G7FR"},"agent_actions":{"view_html":"https://pith.science/pith/QPJ5G7FRYHETEK2LD73Y6S7EGM","download_json":"https://pith.science/pith/QPJ5G7FRYHETEK2LD73Y6S7EGM.json","view_paper":"https://pith.science/paper/QPJ5G7FR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.19654&json=true","fetch_graph":"https://pith.science/api/pith-number/QPJ5G7FRYHETEK2LD73Y6S7EGM/graph.json","fetch_events":"https://pith.science/api/pith-number/QPJ5G7FRYHETEK2LD73Y6S7EGM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QPJ5G7FRYHETEK2LD73Y6S7EGM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QPJ5G7FRYHETEK2LD73Y6S7EGM/action/storage_attestation","attest_author":"https://pith.science/pith/QPJ5G7FRYHETEK2LD73Y6S7EGM/action/author_attestation","sign_citation":"https://pith.science/pith/QPJ5G7FRYHETEK2LD73Y6S7EGM/action/citation_signature","submit_replication":"https://pith.science/pith/QPJ5G7FRYHETEK2LD73Y6S7EGM/action/replication_record"}},"created_at":"2026-07-05T10:41:22.903024+00:00","updated_at":"2026-07-05T10:41:22.903024+00:00"}