{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3YLEZCMYTED54ULOGXSBITP77H","short_pith_number":"pith:3YLEZCMY","schema_version":"1.0","canonical_sha256":"de164c89989907de516e35e4144dfff9f765ef71ac09987c356d97803f5f9a6d","source":{"kind":"arxiv","id":"2606.17449","version":1},"attestation_state":"computed","paper":{"title":"MODE-RAG: Manifold Outlier Diagnosis and Energy-based Retrieval-Augmented Generation Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG","cs.MM"],"primary_cat":"cs.CL","authors_text":"Jiamin Yan, Jiaxin Dai, Xiang Xiang, Zehang Wei","submitted_at":"2026-06-16T03:06:35Z","abstract_excerpt":"While Multimodal Retrieval-Augmented Generation (M-RAG) enhances Large Vision-Language Models, it remains highly susceptible to cross-modal hallucinations, causal fabrications, and sycophancy. Furthermore, existing mitigation pipelines often face an intervention paradox: static rules tend to unnecessarily disrupt accurate generations, whereas leaving the multi-modal reasoning completely unguided allows existing mismatches to cascade into severe logical fabrications. To quantify and mitigate these hallucinations, we propose a Multi-Agent system, MODE-RAG, driven by Variational Free Energy (VFE)"},"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":"2606.17449","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-16T03:06:35Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG","cs.MM"],"title_canon_sha256":"1cee674632570741a7a39e97608c9d9cc79a2044f3962357fae8f704bfedf65b","abstract_canon_sha256":"fd641308445b7a279580b8e804e667583ad86a10fdef7cd5d24b43af87b1bb79"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:10:13.363378Z","signature_b64":"k5YXz+CfLZdcofdWDN8i+9VmCKvKME/aRbCSSc0SH25hTF6mTiGOuDVfayTaH3RisxWXJg+jKAABhVQ656FgAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de164c89989907de516e35e4144dfff9f765ef71ac09987c356d97803f5f9a6d","last_reissued_at":"2026-06-19T16:10:13.363004Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:10:13.363004Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MODE-RAG: Manifold Outlier Diagnosis and Energy-based Retrieval-Augmented Generation Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG","cs.MM"],"primary_cat":"cs.CL","authors_text":"Jiamin Yan, Jiaxin Dai, Xiang Xiang, Zehang Wei","submitted_at":"2026-06-16T03:06:35Z","abstract_excerpt":"While Multimodal Retrieval-Augmented Generation (M-RAG) enhances Large Vision-Language Models, it remains highly susceptible to cross-modal hallucinations, causal fabrications, and sycophancy. Furthermore, existing mitigation pipelines often face an intervention paradox: static rules tend to unnecessarily disrupt accurate generations, whereas leaving the multi-modal reasoning completely unguided allows existing mismatches to cascade into severe logical fabrications. To quantify and mitigate these hallucinations, we propose a Multi-Agent system, MODE-RAG, driven by Variational Free Energy (VFE)"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.17449","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/2606.17449/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":"2606.17449","created_at":"2026-06-19T16:10:13.363069+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.17449v1","created_at":"2026-06-19T16:10:13.363069+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.17449","created_at":"2026-06-19T16:10:13.363069+00:00"},{"alias_kind":"pith_short_12","alias_value":"3YLEZCMYTED5","created_at":"2026-06-19T16:10:13.363069+00:00"},{"alias_kind":"pith_short_16","alias_value":"3YLEZCMYTED54ULO","created_at":"2026-06-19T16:10:13.363069+00:00"},{"alias_kind":"pith_short_8","alias_value":"3YLEZCMY","created_at":"2026-06-19T16:10:13.363069+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/3YLEZCMYTED54ULOGXSBITP77H","json":"https://pith.science/pith/3YLEZCMYTED54ULOGXSBITP77H.json","graph_json":"https://pith.science/api/pith-number/3YLEZCMYTED54ULOGXSBITP77H/graph.json","events_json":"https://pith.science/api/pith-number/3YLEZCMYTED54ULOGXSBITP77H/events.json","paper":"https://pith.science/paper/3YLEZCMY"},"agent_actions":{"view_html":"https://pith.science/pith/3YLEZCMYTED54ULOGXSBITP77H","download_json":"https://pith.science/pith/3YLEZCMYTED54ULOGXSBITP77H.json","view_paper":"https://pith.science/paper/3YLEZCMY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.17449&json=true","fetch_graph":"https://pith.science/api/pith-number/3YLEZCMYTED54ULOGXSBITP77H/graph.json","fetch_events":"https://pith.science/api/pith-number/3YLEZCMYTED54ULOGXSBITP77H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3YLEZCMYTED54ULOGXSBITP77H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3YLEZCMYTED54ULOGXSBITP77H/action/storage_attestation","attest_author":"https://pith.science/pith/3YLEZCMYTED54ULOGXSBITP77H/action/author_attestation","sign_citation":"https://pith.science/pith/3YLEZCMYTED54ULOGXSBITP77H/action/citation_signature","submit_replication":"https://pith.science/pith/3YLEZCMYTED54ULOGXSBITP77H/action/replication_record"}},"created_at":"2026-06-19T16:10:13.363069+00:00","updated_at":"2026-06-19T16:10:13.363069+00:00"}