{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:CBKCSWUM2W3OLUVBLRGAD7P4ND","short_pith_number":"pith:CBKCSWUM","canonical_record":{"source":{"id":"2506.20639","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-25T17:35:47Z","cross_cats_sorted":[],"title_canon_sha256":"12c3bf5233386fd910b277158330abfe0f74d4c3df0d4d562aabd361d249a508","abstract_canon_sha256":"23d55999f610997c3328e403305a6560c066bf9e983590f3cf05c8402edd8cf8"},"schema_version":"1.0"},"canonical_sha256":"1054295a8cd5b6e5d2a15c4c01fdfc68c9ed59189346dc41310fbdfbf041426c","source":{"kind":"arxiv","id":"2506.20639","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.20639","created_at":"2026-07-05T11:27:32Z"},{"alias_kind":"arxiv_version","alias_value":"2506.20639v2","created_at":"2026-07-05T11:27:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.20639","created_at":"2026-07-05T11:27:32Z"},{"alias_kind":"pith_short_12","alias_value":"CBKCSWUM2W3O","created_at":"2026-07-05T11:27:32Z"},{"alias_kind":"pith_short_16","alias_value":"CBKCSWUM2W3OLUVB","created_at":"2026-07-05T11:27:32Z"},{"alias_kind":"pith_short_8","alias_value":"CBKCSWUM","created_at":"2026-07-05T11:27:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:CBKCSWUM2W3OLUVBLRGAD7P4ND","target":"record","payload":{"canonical_record":{"source":{"id":"2506.20639","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-25T17:35:47Z","cross_cats_sorted":[],"title_canon_sha256":"12c3bf5233386fd910b277158330abfe0f74d4c3df0d4d562aabd361d249a508","abstract_canon_sha256":"23d55999f610997c3328e403305a6560c066bf9e983590f3cf05c8402edd8cf8"},"schema_version":"1.0"},"canonical_sha256":"1054295a8cd5b6e5d2a15c4c01fdfc68c9ed59189346dc41310fbdfbf041426c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:27:32.122085Z","signature_b64":"8ELKAFUnwhLjrEebr65PTF4j6lqaPdNs40xfBK3j8KArQbH7hqqA84LUghD+1WWY0wMPhSqtJpt62zS0nK2qCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1054295a8cd5b6e5d2a15c4c01fdfc68c9ed59189346dc41310fbdfbf041426c","last_reissued_at":"2026-07-05T11:27:32.121619Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:27:32.121619Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.20639","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:27:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QQ6P5qZsGKcWUcTFsX8HKEedheOQogHK2RxUL7B9DpP0Z28Ux799w0GjaugRUzvbWsTeQzBLeiC5+xDCp1SuDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T03:55:08.482285Z"},"content_sha256":"af13f32efca0d17ad6609624d3c4fbb33393782f19d6ae62a57fa2585920a1aa","schema_version":"1.0","event_id":"sha256:af13f32efca0d17ad6609624d3c4fbb33393782f19d6ae62a57fa2585920a1aa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:CBKCSWUM2W3OLUVBLRGAD7P4ND","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Huangjie Zheng, Jiatao Gu, Lingpeng Kong, Navdeep Jaitly, Ruixiang Zhang, Shansan Gong, Yizhe Zhang","submitted_at":"2025-06-25T17:35:47Z","abstract_excerpt":"Diffusion large language models (dLLMs) are compelling alternatives to autoregressive (AR) models because their denoising models operate over the entire sequence. The global planning and iterative refinement features of dLLMs are particularly useful for code generation. However, current training and inference mechanisms for dLLMs in coding are still under-explored. To demystify the decoding behavior of dLLMs and unlock their potential for coding, we systematically investigate their denoising processes and reinforcement learning (RL) methods. We train a 7B dLLM, \\textbf{DiffuCoder}, on 130B tok"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.20639","kind":"arxiv","version":2},"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/2506.20639/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:27:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Zi2MFlhT/D8lMH8POfqUInxlKNVKRxCbK5rsdRUVpZuWrOqP1aEOm4Kb++PuL/HJGx9KInh697Szxx7iL8CNCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T03:55:08.482672Z"},"content_sha256":"02ff5a01ec7bc5caf4d19d385b6ada90c01b5e355dca8a258cbd384656974420","schema_version":"1.0","event_id":"sha256:02ff5a01ec7bc5caf4d19d385b6ada90c01b5e355dca8a258cbd384656974420"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CBKCSWUM2W3OLUVBLRGAD7P4ND/bundle.json","state_url":"https://pith.science/pith/CBKCSWUM2W3OLUVBLRGAD7P4ND/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CBKCSWUM2W3OLUVBLRGAD7P4ND/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":"2026-07-12T03:55:08Z","links":{"resolver":"https://pith.science/pith/CBKCSWUM2W3OLUVBLRGAD7P4ND","bundle":"https://pith.science/pith/CBKCSWUM2W3OLUVBLRGAD7P4ND/bundle.json","state":"https://pith.science/pith/CBKCSWUM2W3OLUVBLRGAD7P4ND/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CBKCSWUM2W3OLUVBLRGAD7P4ND/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CBKCSWUM2W3OLUVBLRGAD7P4ND","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":"23d55999f610997c3328e403305a6560c066bf9e983590f3cf05c8402edd8cf8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-25T17:35:47Z","title_canon_sha256":"12c3bf5233386fd910b277158330abfe0f74d4c3df0d4d562aabd361d249a508"},"schema_version":"1.0","source":{"id":"2506.20639","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.20639","created_at":"2026-07-05T11:27:32Z"},{"alias_kind":"arxiv_version","alias_value":"2506.20639v2","created_at":"2026-07-05T11:27:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.20639","created_at":"2026-07-05T11:27:32Z"},{"alias_kind":"pith_short_12","alias_value":"CBKCSWUM2W3O","created_at":"2026-07-05T11:27:32Z"},{"alias_kind":"pith_short_16","alias_value":"CBKCSWUM2W3OLUVB","created_at":"2026-07-05T11:27:32Z"},{"alias_kind":"pith_short_8","alias_value":"CBKCSWUM","created_at":"2026-07-05T11:27:32Z"}],"graph_snapshots":[{"event_id":"sha256:02ff5a01ec7bc5caf4d19d385b6ada90c01b5e355dca8a258cbd384656974420","target":"graph","created_at":"2026-07-05T11:27:32Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.20639/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion large language models (dLLMs) are compelling alternatives to autoregressive (AR) models because their denoising models operate over the entire sequence. The global planning and iterative refinement features of dLLMs are particularly useful for code generation. However, current training and inference mechanisms for dLLMs in coding are still under-explored. To demystify the decoding behavior of dLLMs and unlock their potential for coding, we systematically investigate their denoising processes and reinforcement learning (RL) methods. We train a 7B dLLM, \\textbf{DiffuCoder}, on 130B tok","authors_text":"Huangjie Zheng, Jiatao Gu, Lingpeng Kong, Navdeep Jaitly, Ruixiang Zhang, Shansan Gong, Yizhe Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-25T17:35:47Z","title":"DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.20639","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:af13f32efca0d17ad6609624d3c4fbb33393782f19d6ae62a57fa2585920a1aa","target":"record","created_at":"2026-07-05T11:27:32Z","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":"23d55999f610997c3328e403305a6560c066bf9e983590f3cf05c8402edd8cf8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-25T17:35:47Z","title_canon_sha256":"12c3bf5233386fd910b277158330abfe0f74d4c3df0d4d562aabd361d249a508"},"schema_version":"1.0","source":{"id":"2506.20639","kind":"arxiv","version":2}},"canonical_sha256":"1054295a8cd5b6e5d2a15c4c01fdfc68c9ed59189346dc41310fbdfbf041426c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1054295a8cd5b6e5d2a15c4c01fdfc68c9ed59189346dc41310fbdfbf041426c","first_computed_at":"2026-07-05T11:27:32.121619Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:27:32.121619Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8ELKAFUnwhLjrEebr65PTF4j6lqaPdNs40xfBK3j8KArQbH7hqqA84LUghD+1WWY0wMPhSqtJpt62zS0nK2qCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:27:32.122085Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.20639","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:af13f32efca0d17ad6609624d3c4fbb33393782f19d6ae62a57fa2585920a1aa","sha256:02ff5a01ec7bc5caf4d19d385b6ada90c01b5e355dca8a258cbd384656974420"],"state_sha256":"6449aaaf82d23910ecebff9d243cbafc684de7be856f92f2251c98de43c811fe"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IA1dsHizUYMIGvJR4MgG1kf8gxhC3JZkCgCTX/Ja4VyZRZ6/OiZb8+LbZI8DrOlEa7neJ5HmJAyid02XJCJoBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-12T03:55:08.484942Z","bundle_sha256":"b0b8c427a61c6cfa724f6492a9635e55cedc819977972ab01d5cd96c84b4d95e"}}