{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:6GKAZ5ZOSCCBYT5KMXD5YZQGQ4","short_pith_number":"pith:6GKAZ5ZO","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"},"canonical_sha256":"f1940cf72e90841c4faa65c7dc66068732c3aeba10134e5d0cb025f5d628d120","source":{"kind":"arxiv","id":"2510.23538","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.23538","created_at":"2026-05-21T01:04:18Z"},{"alias_kind":"arxiv_version","alias_value":"2510.23538v3","created_at":"2026-05-21T01:04:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.23538","created_at":"2026-05-21T01:04:18Z"},{"alias_kind":"pith_short_12","alias_value":"6GKAZ5ZOSCCB","created_at":"2026-05-21T01:04:18Z"},{"alias_kind":"pith_short_16","alias_value":"6GKAZ5ZOSCCBYT5K","created_at":"2026-05-21T01:04:18Z"},{"alias_kind":"pith_short_8","alias_value":"6GKAZ5ZO","created_at":"2026-05-21T01:04:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:6GKAZ5ZOSCCBYT5KMXD5YZQGQ4","target":"record","payload":{"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"},"canonical_sha256":"f1940cf72e90841c4faa65c7dc66068732c3aeba10134e5d0cb025f5d628d120","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"},"source_kind":"arxiv","source_id":"2510.23538","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-21T01:04:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wKLT5QFoZe8IcuNJQejjmlZRhjljXIkUt68b0o7NgkZbQH/5GgFmNpCwFxY0wdyL+zGig52aEiNXaiR1TY/MBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T00:21:45.574847Z"},"content_sha256":"a733dfe90af812a1e877dcd67b36c0db0d022efedd7bd4629c7814bca32715a7","schema_version":"1.0","event_id":"sha256:a733dfe90af812a1e877dcd67b36c0db0d022efedd7bd4629c7814bca32715a7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:6GKAZ5ZOSCCBYT5KMXD5YZQGQ4","target":"graph","payload":{"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"},"verdict_id":"6ad96179-8f73-4a78-b883-516d27c54acd"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-21T01:04:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w3gPW3ty518zZNn7zdItC0ExNrRpM3qHWK0MQ0r7j8kaGF7RQFqxKrUBaPIK61T+DY1Ve8PDUcOHBLl71NglBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T00:21:45.575785Z"},"content_sha256":"db8815b1ca2e0f0cfc6c8116990f1bf2c14ef319b5ff7c5b2a2518b0e7cd2dbe","schema_version":"1.0","event_id":"sha256:db8815b1ca2e0f0cfc6c8116990f1bf2c14ef319b5ff7c5b2a2518b0e7cd2dbe"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6GKAZ5ZOSCCBYT5KMXD5YZQGQ4/bundle.json","state_url":"https://pith.science/pith/6GKAZ5ZOSCCBYT5KMXD5YZQGQ4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6GKAZ5ZOSCCBYT5KMXD5YZQGQ4/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-24T00:21:45Z","links":{"resolver":"https://pith.science/pith/6GKAZ5ZOSCCBYT5KMXD5YZQGQ4","bundle":"https://pith.science/pith/6GKAZ5ZOSCCBYT5KMXD5YZQGQ4/bundle.json","state":"https://pith.science/pith/6GKAZ5ZOSCCBYT5KMXD5YZQGQ4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6GKAZ5ZOSCCBYT5KMXD5YZQGQ4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6GKAZ5ZOSCCBYT5KMXD5YZQGQ4","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":"58a39ceca1186ce3e0bea2382f3b762ddcf14a35c6fad75c1d47ede1ae0da1eb","cross_cats_sorted":["cs.CL","cs.CV","cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-10-27T17:13:49Z","title_canon_sha256":"4849db6f7f01aec2b0b6cebe79650905d7ef0fe4e69397139a6aefc3e709dfb4"},"schema_version":"1.0","source":{"id":"2510.23538","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.23538","created_at":"2026-05-21T01:04:18Z"},{"alias_kind":"arxiv_version","alias_value":"2510.23538v3","created_at":"2026-05-21T01:04:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.23538","created_at":"2026-05-21T01:04:18Z"},{"alias_kind":"pith_short_12","alias_value":"6GKAZ5ZOSCCB","created_at":"2026-05-21T01:04:18Z"},{"alias_kind":"pith_short_16","alias_value":"6GKAZ5ZOSCCBYT5K","created_at":"2026-05-21T01:04:18Z"},{"alias_kind":"pith_short_8","alias_value":"6GKAZ5ZO","created_at":"2026-05-21T01:04:18Z"}],"graph_snapshots":[{"event_id":"sha256:db8815b1ca2e0f0cfc6c8116990f1bf2c14ef319b5ff7c5b2a2518b0e7cd2dbe","target":"graph","created_at":"2026-05-21T01:04:18Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A single model trained on synthetic multimodal data creates a visual-programmatic interface that generates code from text, images, or both."}],"snapshot_sha256":"29a80baed31fb0214fe50da7f0ef3e9fdf4cca53c19cf753c97d18dacc294c5d"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"e1489c221a298059dc0375fe0ba90abb7eaee4d6c4ac565e62edd6cbe469f9cb"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2510.23538/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Ben Kao, Fei Yuan, Jingyang Gong, Kai Chen, Lei Li, Qiaosheng Chen, Qipeng Guo, Qiushi Sun, Yang Liu","cross_cats":["cs.CL","cs.CV","cs.SE"],"headline":"A single model trained on synthetic multimodal data creates a visual-programmatic interface that generates code from text, images, or both.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-10-27T17:13:49Z","title":"JanusCoder: Towards a Foundational Visual-Programmatic Interface for Code Intelligence"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.23538","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-18T04:04:02.016344Z","id":"6ad96179-8f73-4a78-b883-516d27c54acd","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"A single model trained on synthetic multimodal data creates a visual-programmatic interface that generates code from text, images, or both.","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.","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."}},"verdict_id":"6ad96179-8f73-4a78-b883-516d27c54acd"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a733dfe90af812a1e877dcd67b36c0db0d022efedd7bd4629c7814bca32715a7","target":"record","created_at":"2026-05-21T01:04:18Z","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":"58a39ceca1186ce3e0bea2382f3b762ddcf14a35c6fad75c1d47ede1ae0da1eb","cross_cats_sorted":["cs.CL","cs.CV","cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-10-27T17:13:49Z","title_canon_sha256":"4849db6f7f01aec2b0b6cebe79650905d7ef0fe4e69397139a6aefc3e709dfb4"},"schema_version":"1.0","source":{"id":"2510.23538","kind":"arxiv","version":3}},"canonical_sha256":"f1940cf72e90841c4faa65c7dc66068732c3aeba10134e5d0cb025f5d628d120","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f1940cf72e90841c4faa65c7dc66068732c3aeba10134e5d0cb025f5d628d120","first_computed_at":"2026-05-21T01:04:18.083080Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T01:04:18.083080Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rkVZOcZmDJYl5N3IneQfnSAWh7l6vqLV5kLryHNMpFwzGWjKyiDFAKrtIz0Q5zSrhBL+Rnp7FNEhOJ2j1TLNBQ==","signature_status":"signed_v1","signed_at":"2026-05-21T01:04:18.084038Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.23538","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a733dfe90af812a1e877dcd67b36c0db0d022efedd7bd4629c7814bca32715a7","sha256:db8815b1ca2e0f0cfc6c8116990f1bf2c14ef319b5ff7c5b2a2518b0e7cd2dbe"],"state_sha256":"01227a9b38596acccdbf5926f306c97454877654e416d146beeb050d0d83b856"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JXPatGPP4wlpcFXCiG14/hQ2mLZwgoR61frhFCnWQvakbPaM926SUnD279RKWiYq5CxvZ+B9y/wLIkqAx9uaDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-24T00:21:45.580001Z","bundle_sha256":"458606577a70f963f761deb75f2160cf8220370487cad2041e0add760ff21400"}}