{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CAH45CJZEXVLNYYSISZLVA53PL","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":"91938c141c6550be5dd82d46b47c27aa08563ecbf34ec617820ce2eefb8f04f2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-23T08:18:00Z","title_canon_sha256":"cfa1c72cdf61b12aa172132dbfb35f966ad9323bd89105994fa69e6b141e3fd8"},"schema_version":"1.0","source":{"id":"2505.17609","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.17609","created_at":"2026-07-05T11:53:03Z"},{"alias_kind":"arxiv_version","alias_value":"2505.17609v2","created_at":"2026-07-05T11:53:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17609","created_at":"2026-07-05T11:53:03Z"},{"alias_kind":"pith_short_12","alias_value":"CAH45CJZEXVL","created_at":"2026-07-05T11:53:03Z"},{"alias_kind":"pith_short_16","alias_value":"CAH45CJZEXVLNYYS","created_at":"2026-07-05T11:53:03Z"},{"alias_kind":"pith_short_8","alias_value":"CAH45CJZ","created_at":"2026-07-05T11:53:03Z"}],"graph_snapshots":[{"event_id":"sha256:9cee100d8704c39adf8fe1dc2336550a50ac2099ed343a617bf106eaf6815e09","target":"graph","created_at":"2026-07-05T11:53:03Z","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/2505.17609/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current large vision-language models (LVLMs) typically employ a connector module to link visual features with text embeddings of large language models (LLMs) and use end-to-end training to achieve multi-modal understanding in a unified process. Effective alignment needs high-quality pre-training data and a carefully designed training process. Current LVLMs face challenges when addressing complex vision-language reasoning tasks, with their reasoning capabilities notably lagging behind those of LLMs. This paper proposes a paradigm shift: instead of training end-to-end vision-language reasoning m","authors_text":"Jinfeng Bai, Lei Zhang, Ming Liu, Qilong Wang, Wangmeng Zuo, Zhilong Ji, Zixian Guo","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-23T08:18:00Z","title":"Integrating Visual Interpretation and Linguistic Reasoning for Math Problem Solving"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17609","kind":"arxiv","version":2},"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":"sha256:6a3365edd4f6fcfde4af8e2ac99481a529758438a1b30c981ee8dcfc5ed2162e","target":"record","created_at":"2026-07-05T11:53:03Z","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":"91938c141c6550be5dd82d46b47c27aa08563ecbf34ec617820ce2eefb8f04f2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-23T08:18:00Z","title_canon_sha256":"cfa1c72cdf61b12aa172132dbfb35f966ad9323bd89105994fa69e6b141e3fd8"},"schema_version":"1.0","source":{"id":"2505.17609","kind":"arxiv","version":2}},"canonical_sha256":"100fce893925eab6e31244b2ba83bb7adabadde223642574453cc8039c4893f8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"100fce893925eab6e31244b2ba83bb7adabadde223642574453cc8039c4893f8","first_computed_at":"2026-07-05T11:53:03.368334Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:53:03.368334Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+kAOfC+mUNqSq/63niZtEiq/4jMfNeiPgAJt0CDf8Mvm9cTv9oohGc06Cgrwu2HGSWjOqpkI8UBvZhHO4uayAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:53:03.368816Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.17609","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6a3365edd4f6fcfde4af8e2ac99481a529758438a1b30c981ee8dcfc5ed2162e","sha256:9cee100d8704c39adf8fe1dc2336550a50ac2099ed343a617bf106eaf6815e09"],"state_sha256":"78f46696649d67a024d0318ebf0c773ebdda61c79c087242d43f3b3e8f5bd5f4"}