{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QOI2LKVC7OQPRNAV2XOOIA4OK5","short_pith_number":"pith:QOI2LKVC","schema_version":"1.0","canonical_sha256":"8391a5aaa2fba0f8b415d5dce4038e575936e105dde226a6443f150a39b4a561","source":{"kind":"arxiv","id":"2606.31732","version":1},"attestation_state":"computed","paper":{"title":"UniCoder: Unified Visual-to-Code Generation via Symbolic Rewards and Reference-Guided Code Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Zhang, Kaituo Feng, Manyuan Zhang, Tianshuo Peng, Xiangyu Yue, Yaozhi Zheng, Yilei Jiang, Yuxuan Wan","submitted_at":"2026-06-30T14:29:48Z","abstract_excerpt":"Visual-to-Code generation, which transforms scientific plots, vector graphics, and webpages into executable scripts, demands a level of pixel-precise alignment that standard Multimodal Large Language Models (MLLMs) fail to achieve through Supervised Fine-Tuning (SFT) alone. While Reinforcement Learning (RL) offers a theoretical pathway to bridge this gap, its application is hindered by two fundamental obstacles: (1) \\textit{Reward Coarseness}, where semantic metrics like CLIP scores fail to penalize fine-grained element deviations, and (2) \\textit{Exploration Stagnation}, where the sparse, het"},"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":"2606.31732","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-30T14:29:48Z","cross_cats_sorted":[],"title_canon_sha256":"5dca8619a20e9bc10cd03b509184ea366270bfc844808add7e21253358b54195","abstract_canon_sha256":"c610679fed32f22b379e8713e06533290697b22f5081acb8369c0552eec54b06"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T01:18:13.128049Z","signature_b64":"qI4PkpoKQtKt4/QDHFKc6Sm/Se6pxxexULpt7MTOtG9sFvHSdmTbPzSASNMnlWAFY71mHX/plNKqvE7l0dd8AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8391a5aaa2fba0f8b415d5dce4038e575936e105dde226a6443f150a39b4a561","last_reissued_at":"2026-07-01T01:18:13.127556Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T01:18:13.127556Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniCoder: Unified Visual-to-Code Generation via Symbolic Rewards and Reference-Guided Code Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Zhang, Kaituo Feng, Manyuan Zhang, Tianshuo Peng, Xiangyu Yue, Yaozhi Zheng, Yilei Jiang, Yuxuan Wan","submitted_at":"2026-06-30T14:29:48Z","abstract_excerpt":"Visual-to-Code generation, which transforms scientific plots, vector graphics, and webpages into executable scripts, demands a level of pixel-precise alignment that standard Multimodal Large Language Models (MLLMs) fail to achieve through Supervised Fine-Tuning (SFT) alone. While Reinforcement Learning (RL) offers a theoretical pathway to bridge this gap, its application is hindered by two fundamental obstacles: (1) \\textit{Reward Coarseness}, where semantic metrics like CLIP scores fail to penalize fine-grained element deviations, and (2) \\textit{Exploration Stagnation}, where the sparse, het"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.31732","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/2606.31732/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":"2606.31732","created_at":"2026-07-01T01:18:13.127637+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.31732v1","created_at":"2026-07-01T01:18:13.127637+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.31732","created_at":"2026-07-01T01:18:13.127637+00:00"},{"alias_kind":"pith_short_12","alias_value":"QOI2LKVC7OQP","created_at":"2026-07-01T01:18:13.127637+00:00"},{"alias_kind":"pith_short_16","alias_value":"QOI2LKVC7OQPRNAV","created_at":"2026-07-01T01:18:13.127637+00:00"},{"alias_kind":"pith_short_8","alias_value":"QOI2LKVC","created_at":"2026-07-01T01:18:13.127637+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/QOI2LKVC7OQPRNAV2XOOIA4OK5","json":"https://pith.science/pith/QOI2LKVC7OQPRNAV2XOOIA4OK5.json","graph_json":"https://pith.science/api/pith-number/QOI2LKVC7OQPRNAV2XOOIA4OK5/graph.json","events_json":"https://pith.science/api/pith-number/QOI2LKVC7OQPRNAV2XOOIA4OK5/events.json","paper":"https://pith.science/paper/QOI2LKVC"},"agent_actions":{"view_html":"https://pith.science/pith/QOI2LKVC7OQPRNAV2XOOIA4OK5","download_json":"https://pith.science/pith/QOI2LKVC7OQPRNAV2XOOIA4OK5.json","view_paper":"https://pith.science/paper/QOI2LKVC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.31732&json=true","fetch_graph":"https://pith.science/api/pith-number/QOI2LKVC7OQPRNAV2XOOIA4OK5/graph.json","fetch_events":"https://pith.science/api/pith-number/QOI2LKVC7OQPRNAV2XOOIA4OK5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QOI2LKVC7OQPRNAV2XOOIA4OK5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QOI2LKVC7OQPRNAV2XOOIA4OK5/action/storage_attestation","attest_author":"https://pith.science/pith/QOI2LKVC7OQPRNAV2XOOIA4OK5/action/author_attestation","sign_citation":"https://pith.science/pith/QOI2LKVC7OQPRNAV2XOOIA4OK5/action/citation_signature","submit_replication":"https://pith.science/pith/QOI2LKVC7OQPRNAV2XOOIA4OK5/action/replication_record"}},"created_at":"2026-07-01T01:18:13.127637+00:00","updated_at":"2026-07-01T01:18:13.127637+00:00"}