{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NFR7D3TKF5FJXHBHE35KARRZL3","short_pith_number":"pith:NFR7D3TK","schema_version":"1.0","canonical_sha256":"6963f1ee6a2f4a9b9c2726faa046395efde5b325c11605e8d6fbf224148341e0","source":{"kind":"arxiv","id":"2605.11854","version":2},"attestation_state":"computed","paper":{"title":"Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A new optimization framework for diffusion language models uses self-distilled inference trajectories and Boltzmann modeling of entropies to close the gap with standard supervised fine-tuning.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dandan Tu, Haoliang Li, Hui Liu, Kecheng Chen, Lingpeng Kong, Rui Liu, Shi Wu, Suiyun Zhang, Xijia Tao, Xinyu Fu, Yibing Liu, Ziru Liu","submitted_at":"2026-05-12T09:39:06Z","abstract_excerpt":"Diffusion Language Models (DLMs) have recently emerged as a promising alternative to autoregressive language models, offering stronger global awareness and highly parallel generation. However, post-training DLMs with standard Negative Evidence Lower Bound (NELBO)-based supervised fine-tuning remains inefficient: training reconstructs randomly masked tokens in a single step, whereas inference follows a confidence-guided, multi-step easy-to-hard denoising trajectory. Recent trajectory-based self-distillation methods exploit such inference trajectories mainly for sampling-step compression and acc"},"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":"2605.11854","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-12T09:39:06Z","cross_cats_sorted":[],"title_canon_sha256":"81b1fcd3984a8bed55856acf3b3d8e6dbe00b7b2cfc8a57fc276301cb0e49e40","abstract_canon_sha256":"dc78199a10256301f0dcd74b28737650a982dce09dcd11f273d65eb6aabd7b7c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:36.308337Z","signature_b64":"pbGIS9FF3Fbu+muez+vooVkk+EYCAhRYdKOiSK4DecDiIfXLsNU/9lDuESLGT8hirx+YJSztR5y1UdbTmhclCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6963f1ee6a2f4a9b9c2726faa046395efde5b325c11605e8d6fbf224148341e0","last_reissued_at":"2026-05-20T00:04:36.307179Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:36.307179Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A new optimization framework for diffusion language models uses self-distilled inference trajectories and Boltzmann modeling of entropies to close the gap with standard supervised fine-tuning.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dandan Tu, Haoliang Li, Hui Liu, Kecheng Chen, Lingpeng Kong, Rui Liu, Shi Wu, Suiyun Zhang, Xijia Tao, Xinyu Fu, Yibing Liu, Ziru Liu","submitted_at":"2026-05-12T09:39:06Z","abstract_excerpt":"Diffusion Language Models (DLMs) have recently emerged as a promising alternative to autoregressive language models, offering stronger global awareness and highly parallel generation. However, post-training DLMs with standard Negative Evidence Lower Bound (NELBO)-based supervised fine-tuning remains inefficient: training reconstructs randomly masked tokens in a single step, whereas inference follows a confidence-guided, multi-step easy-to-hard denoising trajectory. Recent trajectory-based self-distillation methods exploit such inference trajectories mainly for sampling-step compression and acc"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"TABOM achieves substantial gains in new domains, expands the effective knowledge boundary of DLMs, and significantly mitigates catastrophic forgetting compared with standard SFT.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That modeling the inference unmasking preference as a Boltzmann distribution over predictive entropies and deriving a pairwise ranking objective from it will produce genuine knowledge acquisition rather than marginal or illusory gains.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"TABOM models inference unmasking preferences as a Boltzmann distribution over predictive entropies and derives a ranking loss to align DLM training with observed trajectories, yielding gains in new domains and reduced catastrophic forgetting versus standard SFT.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A new optimization framework for diffusion language models uses self-distilled inference trajectories and Boltzmann modeling of entropies to close the gap with standard supervised fine-tuning.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"39504c315db187e1d938a3635f6991d019c81cf91b39a2672696461f8066250d"},"source":{"id":"2605.11854","kind":"arxiv","version":2},"verdict":{"id":"d6c29f0f-8efb-4c95-87c2-0163a8e682bc","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-13T05:48:46.216040Z","strongest_claim":"TABOM achieves substantial gains in new domains, expands the effective knowledge boundary of DLMs, and significantly mitigates catastrophic forgetting compared with standard SFT.","one_line_summary":"TABOM models inference unmasking preferences as a Boltzmann distribution over predictive entropies and derives a ranking loss to align DLM training with observed trajectories, yielding gains in new domains and reduced catastrophic forgetting versus standard SFT.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That modeling the inference unmasking preference as a Boltzmann distribution over predictive entropies and deriving a pairwise ranking objective from it will produce genuine knowledge acquisition rather than marginal or illusory gains.","pith_extraction_headline":"A new optimization framework for diffusion language models uses self-distilled inference trajectories and Boltzmann modeling of entropies to close the gap with standard supervised fine-tuning."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.11854/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T11:36:39.823964Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T09:01:18.338110Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T08:08:14.829608Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"3e31ee0a46068f7e82e0ecf3caef4096db9c92f52d8a0fa93e0f2efbbc1ea3ad"},"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":"2605.11854","created_at":"2026-05-20T00:04:36.307373+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.11854v2","created_at":"2026-05-20T00:04:36.307373+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.11854","created_at":"2026-05-20T00:04:36.307373+00:00"},{"alias_kind":"pith_short_12","alias_value":"NFR7D3TKF5FJ","created_at":"2026-05-20T00:04:36.307373+00:00"},{"alias_kind":"pith_short_16","alias_value":"NFR7D3TKF5FJXHBH","created_at":"2026-05-20T00:04:36.307373+00:00"},{"alias_kind":"pith_short_8","alias_value":"NFR7D3TK","created_at":"2026-05-20T00:04:36.307373+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.18141","citing_title":"A Brief Overview: On-Policy Self-Distillation In Large Language Models","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18141","citing_title":"A Brief Overview: On-Policy Self-Distillation In Large Language Models","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NFR7D3TKF5FJXHBHE35KARRZL3","json":"https://pith.science/pith/NFR7D3TKF5FJXHBHE35KARRZL3.json","graph_json":"https://pith.science/api/pith-number/NFR7D3TKF5FJXHBHE35KARRZL3/graph.json","events_json":"https://pith.science/api/pith-number/NFR7D3TKF5FJXHBHE35KARRZL3/events.json","paper":"https://pith.science/paper/NFR7D3TK"},"agent_actions":{"view_html":"https://pith.science/pith/NFR7D3TKF5FJXHBHE35KARRZL3","download_json":"https://pith.science/pith/NFR7D3TKF5FJXHBHE35KARRZL3.json","view_paper":"https://pith.science/paper/NFR7D3TK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.11854&json=true","fetch_graph":"https://pith.science/api/pith-number/NFR7D3TKF5FJXHBHE35KARRZL3/graph.json","fetch_events":"https://pith.science/api/pith-number/NFR7D3TKF5FJXHBHE35KARRZL3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NFR7D3TKF5FJXHBHE35KARRZL3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NFR7D3TKF5FJXHBHE35KARRZL3/action/storage_attestation","attest_author":"https://pith.science/pith/NFR7D3TKF5FJXHBHE35KARRZL3/action/author_attestation","sign_citation":"https://pith.science/pith/NFR7D3TKF5FJXHBHE35KARRZL3/action/citation_signature","submit_replication":"https://pith.science/pith/NFR7D3TKF5FJXHBHE35KARRZL3/action/replication_record"}},"created_at":"2026-05-20T00:04:36.307373+00:00","updated_at":"2026-05-20T00:04:36.307373+00:00"}