{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2XH3MDO2ZDM4ELLO5BP7CLZ4LZ","short_pith_number":"pith:2XH3MDO2","schema_version":"1.0","canonical_sha256":"d5cfb60ddac8d9c22d6ee85ff12f3c5e429222fde503bf303318ad5b84d55108","source":{"kind":"arxiv","id":"2605.17214","version":1},"attestation_state":"computed","paper":{"title":"ChemVA: Advancing Large Language Models on Chemical Reaction Diagrams Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.AI","authors_text":"Hao Yu, Huajun Chen, Jiangzhen Fu, Kehua Feng, Keyan Ding, Mingyang Rao, Zhihui Zhu","submitted_at":"2026-05-17T01:12:50Z","abstract_excerpt":"While Large Language Models (LLMs) have revolutionized scientific text processing, they exhibit a significant capability gap when interpreting chemical reaction diagrams. We identify two fundamental bottlenecks restricting current systems: a Visual Deficit, where generic vision encoders struggle to resolve the strict topological connectivity of dense molecular graphs, and a Semantic Disconnect, where standard linear strings, such as SMILES, fail to effectively activate the model's latent chemical reasoning. To bridge these gaps, we propose the Chemical Visual Activation (ChemVA) framework, whi"},"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":"2605.17214","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-17T01:12:50Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"a7c3bf80d8405b0c572f9a6ee9fd02159c6a51d9a3e7948d471a2b8a7db0cd06","abstract_canon_sha256":"471aa944f94b14708cf38f900383144750fef85f93d3370fb90a769f5721a290"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:03:45.621583Z","signature_b64":"3a48nNu6JzhzYF7qY/gSw3Gz0jZGsOXkE5Mc2K29YFqXghDK7wI5kM6X+baSbldIpO7KT0JDAa+eHUv8R4ZCBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d5cfb60ddac8d9c22d6ee85ff12f3c5e429222fde503bf303318ad5b84d55108","last_reissued_at":"2026-05-20T00:03:45.620779Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:03:45.620779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ChemVA: Advancing Large Language Models on Chemical Reaction Diagrams Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.AI","authors_text":"Hao Yu, Huajun Chen, Jiangzhen Fu, Kehua Feng, Keyan Ding, Mingyang Rao, Zhihui Zhu","submitted_at":"2026-05-17T01:12:50Z","abstract_excerpt":"While Large Language Models (LLMs) have revolutionized scientific text processing, they exhibit a significant capability gap when interpreting chemical reaction diagrams. We identify two fundamental bottlenecks restricting current systems: a Visual Deficit, where generic vision encoders struggle to resolve the strict topological connectivity of dense molecular graphs, and a Semantic Disconnect, where standard linear strings, such as SMILES, fail to effectively activate the model's latent chemical reasoning. To bridge these gaps, we propose the Chemical Visual Activation (ChemVA) framework, whi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17214","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/2605.17214/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T22:33:23.723009Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T22:01:57.926745Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"d87bf95bd75bd9c82764f79bda200139119da9236d1a2cfd3c3ff3e0b3c0d33f"},"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":"2605.17214","created_at":"2026-05-20T00:03:45.620887+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.17214v1","created_at":"2026-05-20T00:03:45.620887+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17214","created_at":"2026-05-20T00:03:45.620887+00:00"},{"alias_kind":"pith_short_12","alias_value":"2XH3MDO2ZDM4","created_at":"2026-05-20T00:03:45.620887+00:00"},{"alias_kind":"pith_short_16","alias_value":"2XH3MDO2ZDM4ELLO","created_at":"2026-05-20T00:03:45.620887+00:00"},{"alias_kind":"pith_short_8","alias_value":"2XH3MDO2","created_at":"2026-05-20T00:03:45.620887+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/2XH3MDO2ZDM4ELLO5BP7CLZ4LZ","json":"https://pith.science/pith/2XH3MDO2ZDM4ELLO5BP7CLZ4LZ.json","graph_json":"https://pith.science/api/pith-number/2XH3MDO2ZDM4ELLO5BP7CLZ4LZ/graph.json","events_json":"https://pith.science/api/pith-number/2XH3MDO2ZDM4ELLO5BP7CLZ4LZ/events.json","paper":"https://pith.science/paper/2XH3MDO2"},"agent_actions":{"view_html":"https://pith.science/pith/2XH3MDO2ZDM4ELLO5BP7CLZ4LZ","download_json":"https://pith.science/pith/2XH3MDO2ZDM4ELLO5BP7CLZ4LZ.json","view_paper":"https://pith.science/paper/2XH3MDO2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.17214&json=true","fetch_graph":"https://pith.science/api/pith-number/2XH3MDO2ZDM4ELLO5BP7CLZ4LZ/graph.json","fetch_events":"https://pith.science/api/pith-number/2XH3MDO2ZDM4ELLO5BP7CLZ4LZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2XH3MDO2ZDM4ELLO5BP7CLZ4LZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2XH3MDO2ZDM4ELLO5BP7CLZ4LZ/action/storage_attestation","attest_author":"https://pith.science/pith/2XH3MDO2ZDM4ELLO5BP7CLZ4LZ/action/author_attestation","sign_citation":"https://pith.science/pith/2XH3MDO2ZDM4ELLO5BP7CLZ4LZ/action/citation_signature","submit_replication":"https://pith.science/pith/2XH3MDO2ZDM4ELLO5BP7CLZ4LZ/action/replication_record"}},"created_at":"2026-05-20T00:03:45.620887+00:00","updated_at":"2026-05-20T00:03:45.620887+00:00"}