{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CDRYJLHPYLQKVNIGSVRS5HIJAM","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":"312ec8628e2c34798631a171c0f1ab6b651b0a4f32c1e281e2f9000f4aec9f93","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-09T15:38:11Z","title_canon_sha256":"d62000465252d3d8132e812ec932d3c8a257b9c75bed4252ba58e1966940fd10"},"schema_version":"1.0","source":{"id":"2508.07023","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.07023","created_at":"2026-07-05T11:51:39Z"},{"alias_kind":"arxiv_version","alias_value":"2508.07023v1","created_at":"2026-07-05T11:51:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.07023","created_at":"2026-07-05T11:51:39Z"},{"alias_kind":"pith_short_12","alias_value":"CDRYJLHPYLQK","created_at":"2026-07-05T11:51:39Z"},{"alias_kind":"pith_short_16","alias_value":"CDRYJLHPYLQKVNIG","created_at":"2026-07-05T11:51:39Z"},{"alias_kind":"pith_short_8","alias_value":"CDRYJLHP","created_at":"2026-07-05T11:51:39Z"}],"graph_snapshots":[{"event_id":"sha256:353cb835b2e012a31d67546bbbdd48ebc98d226e30ba048b445f53bfa0623b3d","target":"graph","created_at":"2026-07-05T11:51:39Z","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/2508.07023/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Complex Visual Question Answering (Complex VQA) tasks, which demand sophisticated multi-modal reasoning and external knowledge integration, present significant challenges for existing large vision-language models (LVLMs) often limited by their reliance on high-level global features. To address this, we propose MV-CoRe (Multimodal Visual-Conceptual Reasoning), a novel model designed to enhance Complex VQA performance through the deep fusion of diverse visual and linguistic information. MV-CoRe meticulously integrates global embeddings from pre-trained Vision Large Models (VLMs) and Language Lar","authors_text":"Jiehao Chen, Jingwei Peng, Mateo Alejandro Rojas, Meilin Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-09T15:38:11Z","title":"MV-CoRe: Multimodal Visual-Conceptual Reasoning for Complex Visual Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.07023","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:f87bc352b6b5f7b13dd4de22fce3168618d5519fcc8bd4445b241c0651d8cab5","target":"record","created_at":"2026-07-05T11:51:39Z","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":"312ec8628e2c34798631a171c0f1ab6b651b0a4f32c1e281e2f9000f4aec9f93","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-09T15:38:11Z","title_canon_sha256":"d62000465252d3d8132e812ec932d3c8a257b9c75bed4252ba58e1966940fd10"},"schema_version":"1.0","source":{"id":"2508.07023","kind":"arxiv","version":1}},"canonical_sha256":"10e384acefc2e0aab50695632e9d0903262ad58a94395f9aedb166249790c9c1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"10e384acefc2e0aab50695632e9d0903262ad58a94395f9aedb166249790c9c1","first_computed_at":"2026-07-05T11:51:39.482078Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:51:39.482078Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Y6CWHfo+FHS3FIi6b5o1zE1Vk9WLc7Z05xXtkXolfBThmmwFJN+KW80rFO2ziRqH1fQDuB3/WGy3O/VfBjs3BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:51:39.482504Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.07023","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f87bc352b6b5f7b13dd4de22fce3168618d5519fcc8bd4445b241c0651d8cab5","sha256:353cb835b2e012a31d67546bbbdd48ebc98d226e30ba048b445f53bfa0623b3d"],"state_sha256":"71ba828c7431fe1461db49ccc89cf027976f4b244aed6fcec327f21eedcdb3e1"}