{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:5D3SMP2ALAGYOMMJAE4M3CIY22","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":"0a6ad68ce87cfb8edf6861db46c2987da563b9162dd6d702c8a1328c4f72b5a6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-10T10:52:20Z","title_canon_sha256":"c5a3c2def070baea43156c451cc79cacbe4ebc91df279901d3c11151f813622d"},"schema_version":"1.0","source":{"id":"2608.09424","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.09424","created_at":"2026-08-11T02:22:34Z"},{"alias_kind":"arxiv_version","alias_value":"2608.09424v1","created_at":"2026-08-11T02:22:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.09424","created_at":"2026-08-11T02:22:34Z"},{"alias_kind":"pith_short_12","alias_value":"5D3SMP2ALAGY","created_at":"2026-08-11T02:22:34Z"},{"alias_kind":"pith_short_16","alias_value":"5D3SMP2ALAGYOMMJ","created_at":"2026-08-11T02:22:34Z"},{"alias_kind":"pith_short_8","alias_value":"5D3SMP2A","created_at":"2026-08-11T02:22:34Z"}],"graph_snapshots":[{"event_id":"sha256:596a8251fdfade9b97e89cd3bf39ad9e606b59dbb9be77ee220e4f58b81413fd","target":"graph","created_at":"2026-08-11T02:22:34Z","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/2608.09424/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Autoregressive language models align training and use: generation conditions on a clean prompt, and training predicts future tokens from clean left context. Diffusion language models offer parallel denoising, but native dLLM pretraining can randomly corrupt prompt and continuation tokens together, weakening the clean-prefix interface needed for prompt-conditioned generation. We identify this mismatch for prompt continuation and propose PCD (Prefix-Conditioned Diffusion), a pretraining objective that combines AR prefix supervision with no-shift suffix denoising. At the training-objective level,","authors_text":"Huabin Liu, Jianguo Li, Song Guo, Xiaocheng Lu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-10T10:52:20Z","title":"Reducing Pretraining-Generation Mismatch in Diffusion Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.09424","kind":"arxiv","version":1},"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:ee198d7b1473d7c9d8a417b4ab63a9b6aa185ddb1d61cf9fa2ab1b72f7401402","target":"record","created_at":"2026-08-11T02:22:34Z","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":"0a6ad68ce87cfb8edf6861db46c2987da563b9162dd6d702c8a1328c4f72b5a6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-10T10:52:20Z","title_canon_sha256":"c5a3c2def070baea43156c451cc79cacbe4ebc91df279901d3c11151f813622d"},"schema_version":"1.0","source":{"id":"2608.09424","kind":"arxiv","version":1}},"canonical_sha256":"e8f7263f40580d8731890138cd8918d68b4e64a916e33157fde3acea84de85a2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e8f7263f40580d8731890138cd8918d68b4e64a916e33157fde3acea84de85a2","first_computed_at":"2026-08-11T02:22:34.707702Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-11T02:22:34.707702Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nzdoqpw9AdcuTbJbiReyFnOQaTrE3DirOLDQD/jVtGI3yqiUw0gLAZEEXRBicFHVWEvTFbY8I4daQ4DHZX22DQ==","signature_status":"signed_v1","signed_at":"2026-08-11T02:22:34.709149Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.09424","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ee198d7b1473d7c9d8a417b4ab63a9b6aa185ddb1d61cf9fa2ab1b72f7401402","sha256:596a8251fdfade9b97e89cd3bf39ad9e606b59dbb9be77ee220e4f58b81413fd"],"state_sha256":"e0840028e59597b6a54f93914f246bad4117e8396b2a340d6a0b776115243e0e"}