{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JSARBNPPQEB6TRHAR4FDIM7MUE","short_pith_number":"pith:JSARBNPP","schema_version":"1.0","canonical_sha256":"4c8110b5ef8103e9c4e08f0a3433eca134d9c2d7274f9117b468e1c554555780","source":{"kind":"arxiv","id":"2506.10116","version":1},"attestation_state":"computed","paper":{"title":"ChartReasoner: Code-Driven Modality Bridging for Long-Chain Reasoning in Chart Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bihui Yu, Caijun Jia, Jingxuan Wei, Junnan Zhu, Lei Wang, Nan Xu, QingLi Wang","submitted_at":"2025-06-11T18:55:36Z","abstract_excerpt":"Recently, large language models have shown remarkable reasoning capabilities through long-chain reasoning before responding. However, how to extend this capability to visual reasoning tasks remains an open challenge. Existing multimodal reasoning approaches transfer such visual reasoning task into textual reasoning task via several image-to-text conversions, which often lose critical structural and semantic information embedded in visualizations, especially for tasks like chart question answering that require a large amount of visual details. To bridge this gap, we propose ChartReasoner, a cod"},"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":"2506.10116","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-11T18:55:36Z","cross_cats_sorted":[],"title_canon_sha256":"a2aa5fc38d016251b2a7d0ac0a5cca6f3f54f5c2f5e88413281e70f406da55da","abstract_canon_sha256":"c4204aaf977e4a2dd9239370cf94bf827be706cd364e4ae5f43770a6fe9d1088"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:20:16.779296Z","signature_b64":"H0kzLzA12rs6DAc3pTdfL0KGjxQC/tbDzvCWOdJ7B3VfzZ6ZdQZ6UUezRaZukXeq7b+G86gbrHJGKs1wz2SUBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c8110b5ef8103e9c4e08f0a3433eca134d9c2d7274f9117b468e1c554555780","last_reissued_at":"2026-07-05T11:20:16.778826Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:20:16.778826Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ChartReasoner: Code-Driven Modality Bridging for Long-Chain Reasoning in Chart Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bihui Yu, Caijun Jia, Jingxuan Wei, Junnan Zhu, Lei Wang, Nan Xu, QingLi Wang","submitted_at":"2025-06-11T18:55:36Z","abstract_excerpt":"Recently, large language models have shown remarkable reasoning capabilities through long-chain reasoning before responding. However, how to extend this capability to visual reasoning tasks remains an open challenge. Existing multimodal reasoning approaches transfer such visual reasoning task into textual reasoning task via several image-to-text conversions, which often lose critical structural and semantic information embedded in visualizations, especially for tasks like chart question answering that require a large amount of visual details. To bridge this gap, we propose ChartReasoner, a cod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.10116","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/2506.10116/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":"2506.10116","created_at":"2026-07-05T11:20:16.778894+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.10116v1","created_at":"2026-07-05T11:20:16.778894+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.10116","created_at":"2026-07-05T11:20:16.778894+00:00"},{"alias_kind":"pith_short_12","alias_value":"JSARBNPPQEB6","created_at":"2026-07-05T11:20:16.778894+00:00"},{"alias_kind":"pith_short_16","alias_value":"JSARBNPPQEB6TRHA","created_at":"2026-07-05T11:20:16.778894+00:00"},{"alias_kind":"pith_short_8","alias_value":"JSARBNPP","created_at":"2026-07-05T11:20:16.778894+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.15932","citing_title":"Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01249","citing_title":"Trust Region On-Policy Distillation","ref_index":299,"is_internal_anchor":false},{"citing_arxiv_id":"2601.13606","citing_title":"ChartVerse: Scaling Chart Reasoning via Reliable Programmatic Synthesis from Scratch","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01882","citing_title":"Chart-FR1: Visual Focus-Driven Fine-Grained Reasoning on Dense Charts","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JSARBNPPQEB6TRHAR4FDIM7MUE","json":"https://pith.science/pith/JSARBNPPQEB6TRHAR4FDIM7MUE.json","graph_json":"https://pith.science/api/pith-number/JSARBNPPQEB6TRHAR4FDIM7MUE/graph.json","events_json":"https://pith.science/api/pith-number/JSARBNPPQEB6TRHAR4FDIM7MUE/events.json","paper":"https://pith.science/paper/JSARBNPP"},"agent_actions":{"view_html":"https://pith.science/pith/JSARBNPPQEB6TRHAR4FDIM7MUE","download_json":"https://pith.science/pith/JSARBNPPQEB6TRHAR4FDIM7MUE.json","view_paper":"https://pith.science/paper/JSARBNPP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.10116&json=true","fetch_graph":"https://pith.science/api/pith-number/JSARBNPPQEB6TRHAR4FDIM7MUE/graph.json","fetch_events":"https://pith.science/api/pith-number/JSARBNPPQEB6TRHAR4FDIM7MUE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JSARBNPPQEB6TRHAR4FDIM7MUE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JSARBNPPQEB6TRHAR4FDIM7MUE/action/storage_attestation","attest_author":"https://pith.science/pith/JSARBNPPQEB6TRHAR4FDIM7MUE/action/author_attestation","sign_citation":"https://pith.science/pith/JSARBNPPQEB6TRHAR4FDIM7MUE/action/citation_signature","submit_replication":"https://pith.science/pith/JSARBNPPQEB6TRHAR4FDIM7MUE/action/replication_record"}},"created_at":"2026-07-05T11:20:16.778894+00:00","updated_at":"2026-07-05T11:20:16.778894+00:00"}