{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5LX7T2SOAV7DFO5XQCQUM6K7KB","short_pith_number":"pith:5LX7T2SO","schema_version":"1.0","canonical_sha256":"eaeff9ea4e057e32bbb780a146795f507cebabb2a413d6a7b65d4bdad20304d1","source":{"kind":"arxiv","id":"2608.09145","version":1},"attestation_state":"computed","paper":{"title":"Right Answer, Wrong Heat: Explanation-Aware Evaluation and Thermal-Grounded Feedback for MLLMs on Infrared Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Shinichiro Omachi, Tomo Miyazaki, Xiaofeng Liu, Yaohou Fan, Yongsong Huang","submitted_at":"2026-08-10T05:49:33Z","abstract_excerpt":"General-purpose multimodal large language models (MLLMs) are increasingly applied to infrared images, where they are commonly scored by answer accuracy alone. However, a correct answer does not ensure that the model's explanation is grounded in infrared thermal evidence. We introduce an explanation-aware evaluation framework that separates answer correctness, output-level explanation groundedness, and thermal grounding for infrared visual questions. Using a Dual-LLM Consensus Judge with a preliminary human-anchor calibration check, we find that correct answers can still rely on weak or visible"},"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":"2608.09145","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-10T05:49:33Z","cross_cats_sorted":[],"title_canon_sha256":"519f101eb3962b91c2b541803a12c690cf719c18cb2c9c4b4344cd09c6a32617","abstract_canon_sha256":"0188f6736c4a98a5d56ee47803334c347c13f1e0531f2171a96f223fc4b8d0e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-11T02:21:54.596222Z","signature_b64":"xEA4k1T08BweNN0s4joAWUIdVS40kUUuKE3qpbfSOpxPZk2qNK6eAYZRpROjphIAhrO71zlCCCfRJX4mtCLkAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eaeff9ea4e057e32bbb780a146795f507cebabb2a413d6a7b65d4bdad20304d1","last_reissued_at":"2026-08-11T02:21:54.594661Z","signature_status":"signed_v1","first_computed_at":"2026-08-11T02:21:54.594661Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Right Answer, Wrong Heat: Explanation-Aware Evaluation and Thermal-Grounded Feedback for MLLMs on Infrared Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Shinichiro Omachi, Tomo Miyazaki, Xiaofeng Liu, Yaohou Fan, Yongsong Huang","submitted_at":"2026-08-10T05:49:33Z","abstract_excerpt":"General-purpose multimodal large language models (MLLMs) are increasingly applied to infrared images, where they are commonly scored by answer accuracy alone. However, a correct answer does not ensure that the model's explanation is grounded in infrared thermal evidence. We introduce an explanation-aware evaluation framework that separates answer correctness, output-level explanation groundedness, and thermal grounding for infrared visual questions. Using a Dual-LLM Consensus Judge with a preliminary human-anchor calibration check, we find that correct answers can still rely on weak or visible"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.09145","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/2608.09145/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":"2608.09145","created_at":"2026-08-11T02:21:54.595268+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.09145v1","created_at":"2026-08-11T02:21:54.595268+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.09145","created_at":"2026-08-11T02:21:54.595268+00:00"},{"alias_kind":"pith_short_12","alias_value":"5LX7T2SOAV7D","created_at":"2026-08-11T02:21:54.595268+00:00"},{"alias_kind":"pith_short_16","alias_value":"5LX7T2SOAV7DFO5X","created_at":"2026-08-11T02:21:54.595268+00:00"},{"alias_kind":"pith_short_8","alias_value":"5LX7T2SO","created_at":"2026-08-11T02:21:54.595268+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/5LX7T2SOAV7DFO5XQCQUM6K7KB","json":"https://pith.science/pith/5LX7T2SOAV7DFO5XQCQUM6K7KB.json","graph_json":"https://pith.science/api/pith-number/5LX7T2SOAV7DFO5XQCQUM6K7KB/graph.json","events_json":"https://pith.science/api/pith-number/5LX7T2SOAV7DFO5XQCQUM6K7KB/events.json","paper":"https://pith.science/paper/5LX7T2SO"},"agent_actions":{"view_html":"https://pith.science/pith/5LX7T2SOAV7DFO5XQCQUM6K7KB","download_json":"https://pith.science/pith/5LX7T2SOAV7DFO5XQCQUM6K7KB.json","view_paper":"https://pith.science/paper/5LX7T2SO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.09145&json=true","fetch_graph":"https://pith.science/api/pith-number/5LX7T2SOAV7DFO5XQCQUM6K7KB/graph.json","fetch_events":"https://pith.science/api/pith-number/5LX7T2SOAV7DFO5XQCQUM6K7KB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5LX7T2SOAV7DFO5XQCQUM6K7KB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5LX7T2SOAV7DFO5XQCQUM6K7KB/action/storage_attestation","attest_author":"https://pith.science/pith/5LX7T2SOAV7DFO5XQCQUM6K7KB/action/author_attestation","sign_citation":"https://pith.science/pith/5LX7T2SOAV7DFO5XQCQUM6K7KB/action/citation_signature","submit_replication":"https://pith.science/pith/5LX7T2SOAV7DFO5XQCQUM6K7KB/action/replication_record"}},"created_at":"2026-08-11T02:21:54.595268+00:00","updated_at":"2026-08-11T02:21:54.595268+00:00"}