{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6HIISJWNFRNI3VTGNLF35ET7IK","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":"8abea9dc14e850646ce813eeaa6f806ed4c58f4493e8fe3d9fa7451437f961ee","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-03-17T02:54:16Z","title_canon_sha256":"232dc460b5a450d5ab24e1f34f88dc25201ba622f5956300701ca1b93a866680"},"schema_version":"1.0","source":{"id":"2603.16077","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.16077","created_at":"2026-05-22T01:04:00Z"},{"alias_kind":"arxiv_version","alias_value":"2603.16077v3","created_at":"2026-05-22T01:04:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.16077","created_at":"2026-05-22T01:04:00Z"},{"alias_kind":"pith_short_12","alias_value":"6HIISJWNFRNI","created_at":"2026-05-22T01:04:00Z"},{"alias_kind":"pith_short_16","alias_value":"6HIISJWNFRNI3VTG","created_at":"2026-05-22T01:04:00Z"},{"alias_kind":"pith_short_8","alias_value":"6HIISJWN","created_at":"2026-05-22T01:04:00Z"}],"graph_snapshots":[{"event_id":"sha256:d3380e1002da16893a78b2b5649ecf2d58870125cf805a26ddc34425f417f78d","target":"graph","created_at":"2026-05-22T01:04:00Z","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/2603.16077/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Masked diffusion models (MDM) exhibit superior generalization when learned using a Partial masking scheme (Prime). This approach converts tokens into sub-tokens and models the diffusion process at the sub-token level. We identify two limitations of the MDM-Prime framework. First, we find that the functional form of the subtokenizer significantly increases the cross-entropy loss in the objective when paired with commonly used Byte-Pair-Encoding (BPE) tokenizers. Second, we lack tools to guide the hyperparameter choice of the token granularity in the subtokenizer. To address these limitations, w","authors_text":"Chen-Hao Chao, Chun-Yi Lee, Junwei Quan, Rahul G. Krishnan, Wei-Fang Sun","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-03-17T02:54:16Z","title":"MDM-Prime-v2: Binary Encoding and Index Shuffling Enable Scaling of Diffusion Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.16077","kind":"arxiv","version":3},"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":"sha256:1d7c293fe1f64ea27eaeb22410fc32b94760e162690c2885a8923933f821dbd3","target":"record","created_at":"2026-05-22T01:04:00Z","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":"8abea9dc14e850646ce813eeaa6f806ed4c58f4493e8fe3d9fa7451437f961ee","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-03-17T02:54:16Z","title_canon_sha256":"232dc460b5a450d5ab24e1f34f88dc25201ba622f5956300701ca1b93a866680"},"schema_version":"1.0","source":{"id":"2603.16077","kind":"arxiv","version":3}},"canonical_sha256":"f1d08926cd2c5a8dd6666acbbe927f429659870dedefa854ed2b4d9f84e0a7df","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f1d08926cd2c5a8dd6666acbbe927f429659870dedefa854ed2b4d9f84e0a7df","first_computed_at":"2026-05-22T01:04:00.369794Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:04:00.369794Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4zBABBoPn/IkV6I2RVJjMtio8n2iOgSg5vg0dN/u7b1vnYWU8bPSFslaHseo4wqXjXHQtZSdgePNNxuFJL6eAA==","signature_status":"signed_v1","signed_at":"2026-05-22T01:04:00.370462Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.16077","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1d7c293fe1f64ea27eaeb22410fc32b94760e162690c2885a8923933f821dbd3","sha256:d3380e1002da16893a78b2b5649ecf2d58870125cf805a26ddc34425f417f78d"],"state_sha256":"99c6e934146eaac3ae555ff2174119ebe79aba391d53c2f3015a4020f5219031"}