{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:EKUNAA7XSMP6DPLBATEPOC6YUO","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":"01d051f9d1613e568b239d88ececbc543af80e5c7b8e166cee42be87487d0335","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-18T16:25:17Z","title_canon_sha256":"96fb1b47eb3bd29b225a2e014114a8d3016bd7797c16c55175e71c738b90d788"},"schema_version":"1.0","source":{"id":"2607.16872","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.16872","created_at":"2026-07-21T01:21:03Z"},{"alias_kind":"arxiv_version","alias_value":"2607.16872v1","created_at":"2026-07-21T01:21:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.16872","created_at":"2026-07-21T01:21:03Z"},{"alias_kind":"pith_short_12","alias_value":"EKUNAA7XSMP6","created_at":"2026-07-21T01:21:03Z"},{"alias_kind":"pith_short_16","alias_value":"EKUNAA7XSMP6DPLB","created_at":"2026-07-21T01:21:03Z"},{"alias_kind":"pith_short_8","alias_value":"EKUNAA7X","created_at":"2026-07-21T01:21:03Z"}],"graph_snapshots":[{"event_id":"sha256:da8748a3be9cd73e21dba255e1fe95f59fdfedb8128860831b7fccd86f3ee800","target":"graph","created_at":"2026-07-21T01:21:03Z","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/2607.16872/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion large language models (dLLMs) are a promising alternative to autoregressive generation. However, reasoning-oriented post-training for dLLMs remains challenging. Supervised fine-tuning (SFT) for dLLMs requires dense but often off-policy masked states, while reinforcement learning (RL) relies on sparse rewards or value modeling. This paper proposes \\textbf{trace-based on-policy distillation (TOPD)}, a teacher-supervised framework that transfers reasoning ability to a target dLLM without reward estimation. The key idea is to supervise a dLLM on its own denoising trajectory, focusing on ","authors_text":"Chenhao Yuan, Haolin Ren, Jun Zhao, Kang Liu, Ziyang Huang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-18T16:25:17Z","title":"Trace-Based On-Policy Distillation for Masked Diffusion Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.16872","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":"sha256:9d5eef928b2f727d95f73aed9bf1a4fc70e686fc0b7866a5092ff40aa2785afa","target":"record","created_at":"2026-07-21T01:21:03Z","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":"01d051f9d1613e568b239d88ececbc543af80e5c7b8e166cee42be87487d0335","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-18T16:25:17Z","title_canon_sha256":"96fb1b47eb3bd29b225a2e014114a8d3016bd7797c16c55175e71c738b90d788"},"schema_version":"1.0","source":{"id":"2607.16872","kind":"arxiv","version":1}},"canonical_sha256":"22a8d003f7931fe1bd6104c8f70bd8a38cf9f5bf39604a5d0c845c88e466b01b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"22a8d003f7931fe1bd6104c8f70bd8a38cf9f5bf39604a5d0c845c88e466b01b","first_computed_at":"2026-07-21T01:21:03.281832Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-21T01:21:03.281832Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qEiH9/WoDcC1+5MEmdjRJAk6naEi9LMS6MgYVktQ0blmBF2wrTuXzZQBYzpFsRVtHGstW0+/yQzVGZvMKx12BA==","signature_status":"signed_v1","signed_at":"2026-07-21T01:21:03.282727Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.16872","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9d5eef928b2f727d95f73aed9bf1a4fc70e686fc0b7866a5092ff40aa2785afa","sha256:da8748a3be9cd73e21dba255e1fe95f59fdfedb8128860831b7fccd86f3ee800"],"state_sha256":"9f698b58b5529e663259656f122ed310444a5a2d78973d963fce1da347892eeb"}