{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:I7UXGMYM22MCBLOO2SQQS2JNDF","short_pith_number":"pith:I7UXGMYM","schema_version":"1.0","canonical_sha256":"47e973330cd69820adced4a109692d195583e4a96824b4d53f55c27d092fb965","source":{"kind":"arxiv","id":"2606.17999","version":1},"attestation_state":"computed","paper":{"title":"VoidPadding: Let [VOID] Handle Padding in Masked Diffusion Language Models so that [EOS] Can Focus on Semantic Termination","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alex Lamb, Chunyu Liu, Kaisen Yang, Zhengyang Fan","submitted_at":"2026-06-16T14:46:53Z","abstract_excerpt":"MDLMs generate text by denoising a preallocated masked response canvas, making response-length modeling central to instruction tuning. Existing MDLMs often inherit the autoregressive convention of using repeated \\texttt{[EOS]} tokens for padding during instruction tuning, giving \\texttt{[EOS]} a dual role as both a semantic terminator and a padding token. We show that this dual role is a root cause of \\texttt{[EOS]} overflow under large-block decoding. To decouple these roles, we propose VoidPadding, which introduces \\texttt{[VOID]} for padding and reserves \\texttt{[EOS]} for termination. Duri"},"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":"2606.17999","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-16T14:46:53Z","cross_cats_sorted":[],"title_canon_sha256":"1573385a5cf8f7d73f350dc167e19d00b7e7b45446dddb339b62b5083584d771","abstract_canon_sha256":"3adc3a3714c0838771c73fd28eda2d81e5d72ce56b5fa27d6f4cc14175ba755c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:10:45.545700Z","signature_b64":"TDkAFTu0HceoqJ4WmmJEZMv/ezSS26x9II49/QjhT6MF0J52f915adOx35AgfnEK5uVILpCjZYQFqkttsBuSCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"47e973330cd69820adced4a109692d195583e4a96824b4d53f55c27d092fb965","last_reissued_at":"2026-06-19T16:10:45.545349Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:10:45.545349Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VoidPadding: Let [VOID] Handle Padding in Masked Diffusion Language Models so that [EOS] Can Focus on Semantic Termination","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alex Lamb, Chunyu Liu, Kaisen Yang, Zhengyang Fan","submitted_at":"2026-06-16T14:46:53Z","abstract_excerpt":"MDLMs generate text by denoising a preallocated masked response canvas, making response-length modeling central to instruction tuning. Existing MDLMs often inherit the autoregressive convention of using repeated \\texttt{[EOS]} tokens for padding during instruction tuning, giving \\texttt{[EOS]} a dual role as both a semantic terminator and a padding token. We show that this dual role is a root cause of \\texttt{[EOS]} overflow under large-block decoding. To decouple these roles, we propose VoidPadding, which introduces \\texttt{[VOID]} for padding and reserves \\texttt{[EOS]} for termination. Duri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.17999","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/2606.17999/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":"2606.17999","created_at":"2026-06-19T16:10:45.545415+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.17999v1","created_at":"2026-06-19T16:10:45.545415+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.17999","created_at":"2026-06-19T16:10:45.545415+00:00"},{"alias_kind":"pith_short_12","alias_value":"I7UXGMYM22MC","created_at":"2026-06-19T16:10:45.545415+00:00"},{"alias_kind":"pith_short_16","alias_value":"I7UXGMYM22MCBLOO","created_at":"2026-06-19T16:10:45.545415+00:00"},{"alias_kind":"pith_short_8","alias_value":"I7UXGMYM","created_at":"2026-06-19T16:10:45.545415+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I7UXGMYM22MCBLOO2SQQS2JNDF","json":"https://pith.science/pith/I7UXGMYM22MCBLOO2SQQS2JNDF.json","graph_json":"https://pith.science/api/pith-number/I7UXGMYM22MCBLOO2SQQS2JNDF/graph.json","events_json":"https://pith.science/api/pith-number/I7UXGMYM22MCBLOO2SQQS2JNDF/events.json","paper":"https://pith.science/paper/I7UXGMYM"},"agent_actions":{"view_html":"https://pith.science/pith/I7UXGMYM22MCBLOO2SQQS2JNDF","download_json":"https://pith.science/pith/I7UXGMYM22MCBLOO2SQQS2JNDF.json","view_paper":"https://pith.science/paper/I7UXGMYM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.17999&json=true","fetch_graph":"https://pith.science/api/pith-number/I7UXGMYM22MCBLOO2SQQS2JNDF/graph.json","fetch_events":"https://pith.science/api/pith-number/I7UXGMYM22MCBLOO2SQQS2JNDF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I7UXGMYM22MCBLOO2SQQS2JNDF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I7UXGMYM22MCBLOO2SQQS2JNDF/action/storage_attestation","attest_author":"https://pith.science/pith/I7UXGMYM22MCBLOO2SQQS2JNDF/action/author_attestation","sign_citation":"https://pith.science/pith/I7UXGMYM22MCBLOO2SQQS2JNDF/action/citation_signature","submit_replication":"https://pith.science/pith/I7UXGMYM22MCBLOO2SQQS2JNDF/action/replication_record"}},"created_at":"2026-06-19T16:10:45.545415+00:00","updated_at":"2026-06-19T16:10:45.545415+00:00"}