{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UWBHT3CVQG6M7A4GMS2LUATWMU","short_pith_number":"pith:UWBHT3CV","schema_version":"1.0","canonical_sha256":"a58279ec5581bccf838664b4ba02766515edc141c711750c2d1ca991684a1dde","source":{"kind":"arxiv","id":"2509.01142","version":1},"attestation_state":"computed","paper":{"title":"Dream-Coder 7B: An Open Diffusion Language Model for Code","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiacheng Ye, Jiahui Gao, Jingwei Dong, Lingpeng Kong, Lin Zheng, Shansan Gong, Xin Jiang, Xueliang Zhao, Zhenguo Li, Zhihui Xie, Zirui Wu","submitted_at":"2025-09-01T05:30:56Z","abstract_excerpt":"We present Dream-Coder 7B, an open-source discrete diffusion language model for code generation that exhibits emergent any-order generation capabilities. Unlike traditional autoregressive (AR) models that decode strictly left-to-right, Dream-Coder 7B adaptively determines its decoding strategy based on the coding task: sketch-first generation for complex algorithms, left-to-right generation for straightforward completions, and interleaved reasoning generation for code understanding tasks. We adapt a pretrained AR checkpoint to a discrete diffusion frameworks with a continuous-time weighted cro"},"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":"2509.01142","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-09-01T05:30:56Z","cross_cats_sorted":[],"title_canon_sha256":"b03a9e5528ceef1f658c6b8d46991bf62cc70bc36dcb8fa34a53ccbeb5c108c1","abstract_canon_sha256":"17c4b6f5f76fea8828b65a1e86205840c9e3d226ec70f6ea4a0c81d1b8c7e483"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:02:54.658083Z","signature_b64":"0HUpnB3rlrLtf79r72AQ9HtPeFCPePDoSNIoO1YNuz4P9crv6rS3v1qZi95onie4bioHcn0oZ3Ktxq2Iz8QXAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a58279ec5581bccf838664b4ba02766515edc141c711750c2d1ca991684a1dde","last_reissued_at":"2026-07-05T12:02:54.657447Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:02:54.657447Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dream-Coder 7B: An Open Diffusion Language Model for Code","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiacheng Ye, Jiahui Gao, Jingwei Dong, Lingpeng Kong, Lin Zheng, Shansan Gong, Xin Jiang, Xueliang Zhao, Zhenguo Li, Zhihui Xie, Zirui Wu","submitted_at":"2025-09-01T05:30:56Z","abstract_excerpt":"We present Dream-Coder 7B, an open-source discrete diffusion language model for code generation that exhibits emergent any-order generation capabilities. Unlike traditional autoregressive (AR) models that decode strictly left-to-right, Dream-Coder 7B adaptively determines its decoding strategy based on the coding task: sketch-first generation for complex algorithms, left-to-right generation for straightforward completions, and interleaved reasoning generation for code understanding tasks. We adapt a pretrained AR checkpoint to a discrete diffusion frameworks with a continuous-time weighted cro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.01142","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/2509.01142/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":"2509.01142","created_at":"2026-07-05T12:02:54.657538+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.01142v1","created_at":"2026-07-05T12:02:54.657538+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.01142","created_at":"2026-07-05T12:02:54.657538+00:00"},{"alias_kind":"pith_short_12","alias_value":"UWBHT3CVQG6M","created_at":"2026-07-05T12:02:54.657538+00:00"},{"alias_kind":"pith_short_16","alias_value":"UWBHT3CVQG6M7A4G","created_at":"2026-07-05T12:02:54.657538+00:00"},{"alias_kind":"pith_short_8","alias_value":"UWBHT3CV","created_at":"2026-07-05T12:02:54.657538+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":17,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05722","citing_title":"Nemotron-Labs-Diffusion: A Tri-Mode Language Model Unifying Autoregressive, Diffusion, and Self-Speculation Decoding","ref_index":56,"is_internal_anchor":true},{"citing_arxiv_id":"2606.13795","citing_title":"DiPOD: Diffusion Policy Optimization without Drifting Apart","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04027","citing_title":"MaskForge: Structure-Aware Adaptive Attacks for Jailbreaking Diffusion Large Language Models","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02544","citing_title":"SimSD: Simple Speculative Decoding in Diffusion Language Models","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20199","citing_title":"FlowLM: Few-Step Language Modeling via Diffusion-to-Flow Adaptation","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16342","citing_title":"DACA-GRPO: Denoising-Aware Credit Assignment for Reinforcement Learning in Diffusion Language Models","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17174","citing_title":"Beyond Execution: Static-Analysis Rewards and Hint-Conditioned Diffusion RL for Code Generation","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16829","citing_title":"Constrained Code Generation with Discrete Diffusion","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08302","citing_title":"DMax: Aggressive Parallel Decoding for dLLMs","ref_index":87,"is_internal_anchor":false},{"citing_arxiv_id":"2512.14067","citing_title":"Efficient-DLM: From Autoregressive to Diffusion Language Models, and Beyond in Speed","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08564","citing_title":"Attention-Based Sampler for Diffusion Language Models","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13026","citing_title":"Understanding and Accelerating the Training of Masked Diffusion Language Models","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2512.15745","citing_title":"LLaDA2.0: Scaling Up Diffusion Language Models to 100B","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08134","citing_title":"DARE: Diffusion Language Model Activation Reuse for Efficient Inference","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18739","citing_title":"Discrete Tilt Matching","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08302","citing_title":"DMax: Aggressive Parallel Decoding for dLLMs","ref_index":87,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07924","citing_title":"Trajectory as the Teacher: Few-Step Discrete Flow Matching via Energy-Navigated Distillation","ref_index":80,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UWBHT3CVQG6M7A4GMS2LUATWMU","json":"https://pith.science/pith/UWBHT3CVQG6M7A4GMS2LUATWMU.json","graph_json":"https://pith.science/api/pith-number/UWBHT3CVQG6M7A4GMS2LUATWMU/graph.json","events_json":"https://pith.science/api/pith-number/UWBHT3CVQG6M7A4GMS2LUATWMU/events.json","paper":"https://pith.science/paper/UWBHT3CV"},"agent_actions":{"view_html":"https://pith.science/pith/UWBHT3CVQG6M7A4GMS2LUATWMU","download_json":"https://pith.science/pith/UWBHT3CVQG6M7A4GMS2LUATWMU.json","view_paper":"https://pith.science/paper/UWBHT3CV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.01142&json=true","fetch_graph":"https://pith.science/api/pith-number/UWBHT3CVQG6M7A4GMS2LUATWMU/graph.json","fetch_events":"https://pith.science/api/pith-number/UWBHT3CVQG6M7A4GMS2LUATWMU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UWBHT3CVQG6M7A4GMS2LUATWMU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UWBHT3CVQG6M7A4GMS2LUATWMU/action/storage_attestation","attest_author":"https://pith.science/pith/UWBHT3CVQG6M7A4GMS2LUATWMU/action/author_attestation","sign_citation":"https://pith.science/pith/UWBHT3CVQG6M7A4GMS2LUATWMU/action/citation_signature","submit_replication":"https://pith.science/pith/UWBHT3CVQG6M7A4GMS2LUATWMU/action/replication_record"}},"created_at":"2026-07-05T12:02:54.657538+00:00","updated_at":"2026-07-05T12:02:54.657538+00:00"}