{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6GKAZ5ZOSCCBYT5KMXD5YZQGQ4","short_pith_number":"pith:6GKAZ5ZO","schema_version":"1.0","canonical_sha256":"f1940cf72e90841c4faa65c7dc66068732c3aeba10134e5d0cb025f5d628d120","source":{"kind":"arxiv","id":"2510.23538","version":3},"attestation_state":"computed","paper":{"title":"JanusCoder: Towards a Foundational Visual-Programmatic Interface for Code Intelligence","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A single model trained on synthetic multimodal data creates a visual-programmatic interface that generates code from text, images, or both.","cross_cats":["cs.CL","cs.CV","cs.SE"],"primary_cat":"cs.AI","authors_text":"Ben Kao, Fei Yuan, Jingyang Gong, Kai Chen, Lei Li, Qiaosheng Chen, Qipeng Guo, Qiushi Sun, Yang Liu","submitted_at":"2025-10-27T17:13:49Z","abstract_excerpt":"The scope of neural code intelligence is rapidly expanding beyond text-based source code to encompass the rich visual outputs that programs generate. This visual dimension is critical for advanced applications like flexible content generation and precise, program-driven editing of visualizations. However, progress has been impeded by the scarcity of high-quality multimodal code data, a bottleneck stemming from challenges in synthesis and quality assessment. To address these challenges, we make contributions from both a data and modeling perspective. We first introduce a complete synthesis tool"},"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":true},"canonical_record":{"source":{"id":"2510.23538","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-10-27T17:13:49Z","cross_cats_sorted":["cs.CL","cs.CV","cs.SE"],"title_canon_sha256":"4849db6f7f01aec2b0b6cebe79650905d7ef0fe4e69397139a6aefc3e709dfb4","abstract_canon_sha256":"58a39ceca1186ce3e0bea2382f3b762ddcf14a35c6fad75c1d47ede1ae0da1eb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:04:18.084038Z","signature_b64":"rkVZOcZmDJYl5N3IneQfnSAWh7l6vqLV5kLryHNMpFwzGWjKyiDFAKrtIz0Q5zSrhBL+Rnp7FNEhOJ2j1TLNBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f1940cf72e90841c4faa65c7dc66068732c3aeba10134e5d0cb025f5d628d120","last_reissued_at":"2026-05-21T01:04:18.083080Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:04:18.083080Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"JanusCoder: Towards a Foundational Visual-Programmatic Interface for Code Intelligence","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A single model trained on synthetic multimodal data creates a visual-programmatic interface that generates code from text, images, or both.","cross_cats":["cs.CL","cs.CV","cs.SE"],"primary_cat":"cs.AI","authors_text":"Ben Kao, Fei Yuan, Jingyang Gong, Kai Chen, Lei Li, Qiaosheng Chen, Qipeng Guo, Qiushi Sun, Yang Liu","submitted_at":"2025-10-27T17:13:49Z","abstract_excerpt":"The scope of neural code intelligence is rapidly expanding beyond text-based source code to encompass the rich visual outputs that programs generate. This visual dimension is critical for advanced applications like flexible content generation and precise, program-driven editing of visualizations. However, progress has been impeded by the scarcity of high-quality multimodal code data, a bottleneck stemming from challenges in synthesis and quality assessment. To address these challenges, we make contributions from both a data and modeling perspective. We first introduce a complete synthesis tool"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Our unified model is a departure from existing approaches that build specialized models for isolated tasks. Extensive experiments on both text-centric and vision-centric coding tasks demonstrate the superior performance of the JanusCoder series, with our 7B to 14B scale models approaching or even exceeding the performance of commercial models.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The synthesized JanusCode-800K dataset is assumed to be high-quality and representative enough to train models that generalize to real-world visual-programmatic tasks, without detailed validation against human-created or external benchmarks mentioned in the abstract.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"JanusCoder is a unified visual-programmatic model for code generation from text and/or visual inputs, powered by the new JanusCode-800K multimodal dataset.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A single model trained on synthetic multimodal data creates a visual-programmatic interface that generates code from text, images, or both.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"29a80baed31fb0214fe50da7f0ef3e9fdf4cca53c19cf753c97d18dacc294c5d"},"source":{"id":"2510.23538","kind":"arxiv","version":3},"verdict":{"id":"6ad96179-8f73-4a78-b883-516d27c54acd","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-18T04:04:02.016344Z","strongest_claim":"Our unified model is a departure from existing approaches that build specialized models for isolated tasks. Extensive experiments on both text-centric and vision-centric coding tasks demonstrate the superior performance of the JanusCoder series, with our 7B to 14B scale models approaching or even exceeding the performance of commercial models.","one_line_summary":"JanusCoder is a unified visual-programmatic model for code generation from text and/or visual inputs, powered by the new JanusCode-800K multimodal dataset.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The synthesized JanusCode-800K dataset is assumed to be high-quality and representative enough to train models that generalize to real-world visual-programmatic tasks, without detailed validation against human-created or external benchmarks mentioned in the abstract.","pith_extraction_headline":"A single model trained on synthetic multimodal data creates a visual-programmatic interface that generates code from text, images, or both."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2510.23538/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":2,"snapshot_sha256":"e1489c221a298059dc0375fe0ba90abb7eaee4d6c4ac565e62edd6cbe469f9cb"},"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":"2510.23538","created_at":"2026-05-21T01:04:18.083219+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.23538v3","created_at":"2026-05-21T01:04:18.083219+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.23538","created_at":"2026-05-21T01:04:18.083219+00:00"},{"alias_kind":"pith_short_12","alias_value":"6GKAZ5ZOSCCB","created_at":"2026-05-21T01:04:18.083219+00:00"},{"alias_kind":"pith_short_16","alias_value":"6GKAZ5ZOSCCBYT5K","created_at":"2026-05-21T01:04:18.083219+00:00"},{"alias_kind":"pith_short_8","alias_value":"6GKAZ5ZO","created_at":"2026-05-21T01:04:18.083219+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2603.13224","citing_title":"Visual-ERM: Reward Modeling for Visual Equivalence","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6GKAZ5ZOSCCBYT5KMXD5YZQGQ4","json":"https://pith.science/pith/6GKAZ5ZOSCCBYT5KMXD5YZQGQ4.json","graph_json":"https://pith.science/api/pith-number/6GKAZ5ZOSCCBYT5KMXD5YZQGQ4/graph.json","events_json":"https://pith.science/api/pith-number/6GKAZ5ZOSCCBYT5KMXD5YZQGQ4/events.json","paper":"https://pith.science/paper/6GKAZ5ZO"},"agent_actions":{"view_html":"https://pith.science/pith/6GKAZ5ZOSCCBYT5KMXD5YZQGQ4","download_json":"https://pith.science/pith/6GKAZ5ZOSCCBYT5KMXD5YZQGQ4.json","view_paper":"https://pith.science/paper/6GKAZ5ZO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.23538&json=true","fetch_graph":"https://pith.science/api/pith-number/6GKAZ5ZOSCCBYT5KMXD5YZQGQ4/graph.json","fetch_events":"https://pith.science/api/pith-number/6GKAZ5ZOSCCBYT5KMXD5YZQGQ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6GKAZ5ZOSCCBYT5KMXD5YZQGQ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6GKAZ5ZOSCCBYT5KMXD5YZQGQ4/action/storage_attestation","attest_author":"https://pith.science/pith/6GKAZ5ZOSCCBYT5KMXD5YZQGQ4/action/author_attestation","sign_citation":"https://pith.science/pith/6GKAZ5ZOSCCBYT5KMXD5YZQGQ4/action/citation_signature","submit_replication":"https://pith.science/pith/6GKAZ5ZOSCCBYT5KMXD5YZQGQ4/action/replication_record"}},"created_at":"2026-05-21T01:04:18.083219+00:00","updated_at":"2026-05-21T01:04:18.083219+00:00"}